© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194986
    Prev
    Next
    INDEX
    Explanations

    code assignment and definition

    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_15_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
    ד
    0.43
     was
    0.41
    {
    0.40
    ъл
    0.39
    Blood
    0.39
    was
    0.38
    Blo
    0.38
    }{
    0.38
    لد
    0.37
    from
    0.36
    POSITIVE LOGITS
     Oké
    0.45
     schlecht
    0.43
     Bohemia
    0.43
     いっ
    0.40
     อิ
    0.40
     Балтбет
    0.40
    作业
    0.39
    ंखला
    0.39
     Tokio
    0.38
     জার্মান
    0.38
    Activations Density 0.016%

    No Known Activations