© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34305
    Prev
    Next
    INDEX
    Explanations

    major league baseball

    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_7_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
    as
    1.09
    es
    1.04
    el
    1.03
    ის
    1.00
    ы
    0.96
    ות
    0.95
    وں
    0.94
    يا
    0.93
    ات
    0.93
    اں
    0.89
    POSITIVE LOGITS
    <
    0.68
     a
    0.66
     not
    0.66
    ;
    0.65
    hrer
    0.63
     testAvg
    0.63
     be
    0.62
     bacter
    0.60
    ள்ளது
    0.59
     bagaimana
    0.59
    Activations Density 0.001%

    No Known Activations