© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90116
    Prev
    Next
    INDEX
    Explanations

    SOOO SO

    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_11_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
    る
    0.59
    lass
    0.51
    ड़क
    0.51
    ংকা
    0.51
    (
    0.51
    दृ
    0.51
    FUN
    0.50
    ruvate
    0.50
    픈
    0.50
    es
    0.50
    POSITIVE LOGITS
    ;
    0.66
     abrog
    0.59
    ч
    0.59
    .;
    0.56
    П
    0.56
    邕
    0.56
     अनेक
    0.56
     అనేక
    0.55
     Verkauf
    0.55
     album
    0.55
    Activations Density 0.002%

    No Known Activations