© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45987
    Prev
    Next
    INDEX
    Explanations

    display window and image operations

    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
    すべての
    0.61
     OF
    0.58
    import
    0.55
     Of
    0.54
    Το
    0.52
     Paul
    0.51
    Paul
    0.51
    ２
    0.51
     Acest
    0.50
     всех
    0.49
    POSITIVE LOGITS
    ართ
    0.52
     createCanvas
    0.51
     paraphernalia
    0.51
     pintura
    0.50
     visualizations
    0.49
     warms
    0.49
     visuals
    0.48
    เลือด
    0.48
    вался
    0.47
    راط
    0.46
    Activations Density 0.042%

    No Known Activations