© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81323
    Prev
    Next
    INDEX
    Explanations

    VL, weak, prog

    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_0_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
    il
    1.95
    n
    1.72
    un
    1.67
    y
    1.67
    u
    1.55
    et
    1.54
    as
    1.50
    ные
    1.50
    p
    1.49
    an
    1.46
    POSITIVE LOGITS
    لي
    1.23
    ä
    1.22
    ücht
    1.19
    \
    1.16
    يف
    1.14
    ли
    1.13
     insecticides
    1.13
    ем
    1.13
    ري
    1.08
     earrings
    1.08
    Activations Density 0.000%

    No Known Activations