© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35119
    Prev
    Next
    INDEX
    Explanations

    cat-and-mouse game

    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_3_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
    রা
    0.74
    وية
    0.73
     بسي
    0.65
     разрабо
    0.63
    有可能
    0.63
     العلماء
    0.63
    噵
    0.63
    有多少
    0.62
    ில்
    0.62
     Анто
    0.62
    POSITIVE LOGITS
    in
    1.02
    o
    0.93
    al
    0.84
    ter
    0.84
    1
    0.80
    on
    0.76
    at
    0.75
    Y
    0.75
    ing
    0.75
    h
    0.74
    Activations Density 0.007%

    No Known Activations