© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194903
    Prev
    Next
    INDEX
    Explanations

    Peter

    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_4_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
    ت
    1.18
    ת
    1.12
    '
    0.97
    at
    0.96
    Z
    0.95
    TS
    0.95
    ون
    0.92
    सी
    0.92
    ৯
    0.91
    ೆ
    0.89
    POSITIVE LOGITS
    s
    1.17
    د
    1.02
    籽
    0.88
    да
    0.77
    sg
    0.77
    し
    0.73
    si
    0.73
    ديد
    0.71
    នឹង
    0.71
    sı
    0.71
    Activations Density 0.000%

    No Known Activations