© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208269
    Prev
    Next
    INDEX
    Explanations

    code, equations, and mechanics

    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
    に使
    0.53
    會
    0.48
    invokeLater
    0.48
    <bbox>
    0.47
    '});
    0.46
    صاب
    0.46
    ش
    0.45
    expires
    0.45
    聚
    0.45
    فير
    0.44
    POSITIVE LOGITS
    aint
    0.52
    лоба
    0.50
     (
    0.50
    IW
    0.49
    onski
    0.48
     kiedy
    0.47
     oleh
    0.47
     mot
    0.47
     Developmental
    0.47
     holiday
    0.46
    Activations Density 0.000%

    No Known Activations