© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-TRANSCODER-262K
    4. 99557
    Prev
    Next
    INDEX
    Explanations

    Based on the provided lists:* `MAX_ACTIVATING_TOKENS` includes terms like `civilian`, `grades`, `Officers`, `officer`, `RN`. These relate to people in different roles, ranks, or professions, particularly in organizational or hierarchical contexts.* `TOKENS_AFTER_MAX_ACTIVATING_TOKEN` shows punctuation and short connecting words, suggesting these activating tokens are often part of defining or listing roles.* `TOP_POSITIVE_LOGITS` includes non-English words related to 'employees' or 'workers' (कर्मचारियों, कर्मचारी, pracowników). This hints at the neuron might be looking for people/roles that aren't necessarily "management" or purely technical, but perhaps specific types of personnel.personnel, ranks, roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    बी
    0.43
    ဠ
    0.42
    ₿
    0.41
     CHAN
    0.40
     negara
    0.38
    資金
    0.38
    侵害
    0.38
    Modes
    0.38
     grenades
    0.38
     グレー
    0.38
    POSITIVE LOGITS
    conc
    0.41
     कर्मचारियों
    0.39
    afa
    0.38
     कर्मचारी
    0.37
     pracowników
    0.37
    å
    0.37
    ઑ
    0.37
    တစ်
    0.37
     ሁሉ
    0.37
    ising
    0.37
    Activations Density 0.026%

    No Known Activations