© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257818
    Prev
    Next
    INDEX
    Explanations

    president, first, best, worst

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    🎐
    0.64
    <unused1964>
    0.63
    াহিয়া
    0.63
     trastornos
    0.63
    🎏
    0.61
    芪
    0.60
    Ţ
    0.60
    <unused580>
    0.60
    <unused900>
    0.58
     Atlético
    0.58
    POSITIVE LOGITS
    shot
    0.55
    john
    0.52
    emph
    0.51
     third
    0.50
    ριν
    0.48
    as
    0.48
    third
    0.48
     John
    0.47
    over
    0.47
    port
    0.45
    Activations Density 0.001%

    No Known Activations