© 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. 57775
    Prev
    Next
    INDEX
    Explanations

    comprehensive, obviously

    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
    ʖ
    0.68
    ം
    0.66
     Nazar
    0.64
    ньому
    0.59
    বারের
    0.59
    ថា
    0.59
     bahawa
    0.59
     hearers
    0.58
    ம்
    0.57
    ecture
    0.57
    POSITIVE LOGITS
    ut
    0.63
    ä
    0.63
    é
    0.62
    ע
    0.61
    im
    0.59
    in
    0.58
    ç
    0.57
    ong
    0.57
    <h2>
    0.57
    is
    0.56
    Activations Density 0.004%

    No Known Activations