© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163832
    Prev
    Next
    INDEX
    Explanations

    | used as a separator or for magnitude

    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
     ı
    0.64
     студентов
    0.64
     VARCHAR
    0.62
     inl
    0.60
    Гц
    0.60
     ông
    0.57
     ء
    0.57
     bởi
    0.57
     что
    0.56
     între
    0.55
    POSITIVE LOGITS
    E
    0.63
    ার
    0.63
    .
    0.59
    。
    0.59
    olate
    0.56
    et
    0.55
    il
    0.53
    te
    0.52
     on
    0.52
    olated
    0.52
    Activations Density 0.004%

    No Known Activations