© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59054
    Prev
    Next
    INDEX
    Explanations

    individual, personal

    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
    1
    0.67
    we
    0.64
     Work
    0.63
    ...
    0.62
     U
    0.59
    2
    0.57
    FUN
    0.56
    し
    0.56
    ana
    0.55
     Food
    0.54
    POSITIVE LOGITS
    बूझ
    0.66
    ક્ટ
    0.63
    ್ಟ
    0.59
    ಾಂಶ
    0.59
     Mannschaften
    0.58
     miš
    0.58
     nghiên
    0.57
     sofistic
    0.56
     کي
    0.55
    <unused545>
    0.55
    Activations Density 0.001%

    No Known Activations