© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132256
    Prev
    Next
    INDEX
    Explanations

    rev or brew followed by language or calendar

    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_6_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
    क
    1.29
    사
    1.11
     as
    1.09
    d
    1.09
     казни
    1.09
     ativos
    1.05
    да
    1.05
    addena
    1.05
     aprend
    1.04
     brzo
    1.03
    POSITIVE LOGITS
    ’
    1.22
    /
    0.95
     in
    0.91
    '
    0.90
    .
    0.89
    -
    0.83
    ที่
    0.80
    ↵↵
    0.79
    ney
    0.79
    ו
    0.77
    Activations Density 0.000%

    No Known Activations