© 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. 39228
    Prev
    Next
    INDEX
    Explanations

    child theme, law, tables, path

    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
    는
    0.94
    ü
    0.91
    は
    0.87
    oit
    0.85
    是
    0.79
    >
    0.79
    ä
    0.78
    em
    0.78
    他
    0.77
    จะ
    0.77
    POSITIVE LOGITS
    ime
    0.67
    ’
    0.67
    sam
    0.66
    ాలు
    0.65
    atom
    0.65
    ्स
    0.64
     पॉइंट्स
    0.62
    مد
    0.61
    ס
    0.61
     (
    0.61
    Activations Density 0.008%

    No Known Activations