© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46945
    Prev
    Next
    INDEX
    Explanations

    job description

    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_10_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
    Ϳ
    0.68
     about
    0.67
    感知
    0.66
     aasta
    0.63
     公司
    0.62
     执行
    0.62
     runtime
    0.61
     Whisky
    0.61
     Durango
    0.61
    VhZ
    0.61
    POSITIVE LOGITS
    ת
    1.26
    '
    1.18
    l
    1.05
    ك
    1.00
    an
    0.97
    ت
    0.97
    ل
    0.96
    ל
    0.95
    t
    0.94
    ي
    0.93
    Activations Density 0.002%

    No Known Activations