© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90122
    Prev
    Next
    INDEX
    Explanations

    processing, consulting, units

    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
    ’
    0.95
    ।
    0.71
    سون
    0.66
    ’:
    0.63
    স
    0.63
    ’।
    0.63
    tj
    0.62
    ׳
    0.61
    ।’
    0.60
    슨
    0.59
    POSITIVE LOGITS
    ра
    0.78
    es
    0.73
    ون
    0.73
    ре
    0.72
    am
    0.65
    ot
    0.65
    os
    0.63
    ри
    0.63
    з
    0.56
    ara
    0.55
    Activations Density 0.013%

    No Known Activations