© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35272
    Prev
    Next
    INDEX
    Explanations

    basketball players and terms

    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_11_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
    Precision
    0.59
    فت
    0.57
     tasas
    0.54
    นอน
    0.53
    //
    0.51
    त
    0.51
    უბ
    0.50
    (
    0.50
    Number
    0.48
    Genetic
    0.48
    POSITIVE LOGITS
     à
    0.64
     Story
    0.57
     Leuk
    0.57
     書い
    0.56
     À
    0.55
     ¡
    0.54
     Ã
    0.54
     消
    0.54
     かわいい
    0.54
     діа
    0.54
    Activations Density 0.013%

    No Known Activations