© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11744
    Prev
    Next
    INDEX
    Explanations

    rm, del, clear

    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_13_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
    전
    0.60
    /
    0.56
    К
    0.55
    //
    0.50
    ब
    0.50
    Screens
    0.49
    आज
    0.49
     enables
    0.49
    Law
    0.49
    श
    0.48
    POSITIVE LOGITS
    hidden
    0.62
    hanging
    0.61
     删除
    0.55
    FileInputExcel
    0.54
     Maison
    0.54
     ಸಂಗ
    0.53
    noxious
    0.53
     ты
    0.52
     ಕೆಲಸ
    0.52
     Институт
    0.52
    Activations Density 0.052%

    No Known Activations