© 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
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201967
    Prev
    Next
    INDEX
    Explanations

    YAML file parsing and format

    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_12_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
    ഽ
    0.31
    >]</
    0.29
     ওয়
    0.29
    Inet
    0.27
    AH
    0.27
    uttaa
    0.26
    aminen
    0.26
    Wood
    0.26
     薄
    0.26
     Воло
    0.25
    POSITIVE LOGITS
     rigidly
    0.21
     lex
    0.21
     pathophys
    0.21
     predictably
    0.21
    ኪ
    0.21
    <0xA8>
    0.21
     карка
    0.21
     access
    0.21
     dll
    0.21
    y
    0.21
    Activations Density 0.001%

    No Known Activations