© 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. 25531
    Prev
    Next
    INDEX
    Explanations

    mandate

    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
    s
    0.89
    -
    0.86
    im
    0.85
    ad
    0.83
    ,
    0.81
    h
    0.77
    ن
    0.77
    r
    0.77
    p
    0.77
    il
    0.73
    POSITIVE LOGITS
    簱
    0.76
     Sử
    0.73
     Thực
    0.70
     அவர்கள்
    0.68
     マスター
    0.68
    <unused973>
    0.68
    ૫
    0.67
     ボディ
    0.67
     Kết
    0.66
     カル
    0.66
    Activations Density 0.003%

    No Known Activations