© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 196987
    Prev
    Next
    INDEX
    Explanations

    dynamic analysis, performance, calibration

    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_15_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
     vattum
    0.62
    <unused201>
    0.55
    <unused1873>
    0.55
     clearContext
    0.55
    িপ
    0.54
     nieruchomości
    0.54
    jsonplaceholder
    0.54
    力
    0.54
    лән
    0.54
    <unused383>
    0.54
    POSITIVE LOGITS
    c
    0.70
    f
    0.68
    t
    0.65
    re
    0.62
    te
    0.59
    de
    0.57
     '
    0.54
    pr
    0.54
    g
    0.54
    ru
    0.54
    Activations Density 0.001%

    No Known Activations