© 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. 56779
    Prev
    Next
    INDEX
    Explanations

    filling with material

    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
     κό
    0.61
     അമ
    0.59
    <unused1034>
    0.57
    陨
    0.55
     viaggio
    0.55
    ן
    0.54
    <unused425>
    0.54
     સફળ
    0.53
    <unused674>
    0.53
    ";//
    0.52
    POSITIVE LOGITS
    J
    0.61
    Ş
    0.61
    UN
    0.60
    Й
    0.58
    Э
    0.58
    Ç
    0.57
    avljen
    0.57
    Ч
    0.56
    Мы
    0.56
    W
    0.56
    Activations Density 0.001%

    No Known Activations