© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48803
    Prev
    Next
    INDEX
    Explanations

    luau

    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_10_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
     سي
    0.85
     تغيير
    0.82
     ولي
    0.80
     مكان
    0.77
     ليس
    0.76
     مي‌
    0.75
    ᱗
    0.74
    ovány
    0.73
    minValue
    0.72
     ଆ
    0.71
    POSITIVE LOGITS
    ।
    0.98
     and
    0.88
    י
    0.80
     of
    0.78
    ם
    0.78
    \
    0.77
    ?
    0.77
    ي
    0.75
     is
    0.74
    t
    0.74
    Activations Density 0.000%

    No Known Activations