© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207963
    Prev
    Next
    INDEX
    Explanations

    unprecedented surprising event

    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
     খানের
    0.33
     lubric
    0.33
     vantagem
    0.32
     খানকে
    0.31
    -]
    0.31
     möglichst
    0.31
     बदनाम
    0.31
    Khan
    0.30
     MyDB
    0.30
     "'"
    0.30
    POSITIVE LOGITS
     끊
    0.33
     프
    0.32
     대표
    0.29
     лице
    0.29
    电力
    0.29
     precursor
    0.28
    mleri
    0.28
    ель
    0.28
     корпуса
    0.28
    aceut
    0.28
    Activations Density 0.001%

    No Known Activations