© 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. 50146
    Prev
    Next
    INDEX
    Explanations

    DBSCAN or DBSQL

    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
    4
    0.73
    (
    0.71
    a
    0.70
    ه
    0.68
    5
    0.67
    在
    0.66
    {
    0.65
    h
    0.56
    高
    0.55
    有
    0.54
    POSITIVE LOGITS
    ס
    0.88
     to
    0.73
     توصل
    0.63
     ﺍ
    0.61
     という
    0.60
    ্মান
    0.59
     Bisby
    0.57
     argue
    0.55
    AIN
    0.55
    ਸ
    0.55
    Activations Density 0.000%

    No Known Activations