© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83519
    Prev
    Next
    INDEX
    Explanations

    soft

    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_0_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
     brasile
    1.40
    ()=>{
    1.37
     a
    1.35
     gourd
    1.33
     što
    1.31
     protégé
    1.27
     flores
    1.25
     çok
    1.24
     of
    1.23
     the
    1.21
    POSITIVE LOGITS
    t
    1.92
    ла
    1.81
    ul
    1.73
    ا
    1.71
    ت
    1.71
    ع
    1.66
    ad
    1.59
    ע
    1.57
    on
    1.56
    ,
    1.56
    Activations Density 0.001%

    No Known Activations