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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167036
    Prev
    Next
    INDEX
    Explanations

    deep

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Registers
    0.39
    طف
    0.37
    Filters
    0.37
    위
    0.37
     Registers
    0.37
    如何
    0.36
     Filters
    0.36
    Filtering
    0.36
    Cups
    0.35
    MAS
    0.35
    POSITIVE LOGITS
     Deep
    0.75
    Deep
    0.74
     deep
    0.74
    deep
    0.72
    深
    0.70
     깊
    0.69
     глубо
    0.69
     trans
    0.64
     deepened
    0.61
     deeper
    0.60
    Activations Density 0.001%

    No Known Activations