© 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. 221945
    Prev
    Next
    INDEX
    Explanations

    130 Reform Cas liability

    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
    し
    0.80
     membres
    0.78
    Longueur
    0.78
    لي
    0.78
     لي
    0.77
    ياه
    0.77
    جين
    0.77
    쐞
    0.77
    يل
    0.72
    ште
    0.72
    POSITIVE LOGITS
    ,
    0.75
    :
    0.75
    ).
    0.75
    aol
    0.74
     HA
    0.73
    ing
    0.73
    es
    0.72
    ல்
    0.72
    4
    0.71
    3
    0.71
    Activations Density 0.006%

    No Known Activations