© 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. 61925
    Prev
    Next
    INDEX
    Explanations

    endowments

    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
    ਕਰ
    0.66
     coercion
    0.65
    лькі
    0.63
     hamming
    0.63
    lemme
    0.62
    牺
    0.61
     =
    0.60
    дий
    0.58
     каче
    0.57
    ческому
    0.57
    POSITIVE LOGITS
    m
    0.67
     g
    0.61
    ar
    0.57
     naturali
    0.56
     Amerika
    0.55
     publier
    0.55
    Amerika
    0.55
    w
    0.54
     biod
    0.54
    าร
    0.53
    Activations Density 0.000%

    No Known Activations