© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90515
    Prev
    Next
    INDEX
    Explanations

    decorator, club, case, girl, website, emitter

    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_3_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
    m
    0.77
    म
    0.77
    ম
    0.68
    IAN
    0.67
    بانی
    0.67
    to
    0.66
     قیم
    0.65
    م
    0.65
    ج
    0.65
    ق
    0.64
    POSITIVE LOGITS
    ы
    0.68
    ícia
    0.62
    يمان
    0.62
    ومة
    0.57
     معي
    0.55
     poč
    0.55
     oxid
    0.54
     ents
    0.53
     wodurch
    0.53
    ым
    0.53
    Activations Density 0.003%

    No Known Activations