© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130774
    Prev
    Next
    INDEX
    Explanations

    blizzards

    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
     to
    1.46
    T
    1.45
    Y
    1.42
    D
    1.40
    G
    1.21
    DEFAULT
    1.16
     فی
    1.15
    S
    1.13
    P
    1.13
    TED
    1.13
    POSITIVE LOGITS
    ни
    1.88
    ا
    1.72
    ى
    1.52
    ية
    1.49
    '
    1.47
    ي
    1.46
    م
    1.43
    ку
    1.36
    ем
    1.36
    و
    1.36
    Activations Density 0.000%

    No Known Activations