© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198631
    Prev
    Next
    INDEX
    Explanations

    orange segments

    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_4_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
    ม
    0.99
    م
    0.95
    The
    0.89
    m
    0.88
    am
    0.88
    on
    0.86
    ルの
    0.77
    es
    0.74
    as
    0.74
    -
    0.74
    POSITIVE LOGITS
    ية
    0.86
    కి
    0.78
    يل
    0.77
    ิ
    0.77
    ě
    0.77
    ून
    0.73
    тьяна
    0.73
    ้
    0.71
    ियों
    0.70
    ிகள்
    0.69
    Activations Density 0.003%

    No Known Activations