© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171668
    Prev
    Next
    INDEX
    Explanations

    service call or request

    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_20_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
    鈮
    0.48
    amot
    0.48
    !!!!!!!!
    0.46
     мелдеш
    0.45
     `${
    0.45
    вано
    0.44
    що
    0.44
    铷
    0.43
    لعاب
    0.43
    Saat
    0.42
    POSITIVE LOGITS
    ილი
    0.43
     travelers
    0.40
     nightly
    0.39
     authoritarian
    0.39
     Mongols
    0.39
     الأصل
    0.38
     shoreline
    0.38
     unbeaten
    0.38
    ary
    0.38
     rejuvenating
    0.38
    Activations Density 0.001%

    No Known Activations