© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224482
    Prev
    Next
    INDEX
    Explanations

    Bear, cat, Knights

    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
    ن
    0.91
    ط
    0.88
    น
    0.77
    یک
    0.76
    ل
    0.76
    ال
    0.75
    گ
    0.75
    િક
    0.73
    تب
    0.72
    ح
    0.72
    POSITIVE LOGITS
    es
    0.84
    eing
    0.73
     deportes
    0.68
     bimodule
    0.68
     school
    0.67
    MatchType
    0.67
    elry
    0.65
     шко
    0.65
    eis
    0.65
     stoneware
    0.64
    Activations Density 0.006%

    No Known Activations