© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133502
    Prev
    Next
    INDEX
    Explanations

    Loin, Lode, Lamination, Latch, Lighters

    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_1_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
    ون
    1.01
    0.93
    ية
    0.93
    á
    0.92
    -
    0.87
    يل
    0.83
     are
    0.82
    ى
    0.80
    ä
    0.73
     can
    0.73
    POSITIVE LOGITS
    고
    0.75
    Ма
    0.75
    Ну
    0.75
    Ла
    0.75
    Про
    0.70
    for
    0.70
    activity
    0.70
    Но
    0.69
    Лю
    0.69
    К
    0.69
    Activations Density 0.003%

    No Known Activations