© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24391
    Prev
    Next
    INDEX
    Explanations

    in the sense of

    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_10_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
     (\$
    0.79
     в
    0.74
     tricycle
    0.72
     до
    0.69
     Timatic
    0.68
    <unused1791>
    0.68
     is
    0.66
    iz
    0.66
     (~
    0.66
     of
    0.66
    POSITIVE LOGITS
    我
    0.88
    如何
    0.73
    able
    0.73
    0
    0.73
    所有
    0.71
     aşk
    0.71
    All
    0.69
    判断
    0.68
    5
    0.68
    Ꭳ
    0.68
    Activations Density 0.026%

    No Known Activations