© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38034
    Prev
    Next
    INDEX
    Explanations

    switch gears, change direction, change directory

    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_3_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
    '
    1.09
    *'
    0.95
    '`
    0.93
    '*
    0.89
     smells
    0.88
     lags
    0.87
    '}}
    0.87
    のが
    0.86
     ও
    0.86
     იყო
    0.86
    POSITIVE LOGITS
    с
    1.03
    sh
    0.90
    ä
    0.88
    r
    0.86
    in
    0.85
    র
    0.85
    مان
    0.85
    نه
    0.83
    ل
    0.83
    ست
    0.82
    Activations Density 0.019%

    No Known Activations