© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25722
    Prev
    Next
    INDEX
    Explanations

    "Hello, World!"

    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
    am
    0.97
    im
    0.95
     \
    0.93
    ak
    0.91
    ER
    0.83
    ot
    0.75
    ed
    0.73
    om
    0.71
    ir
    0.71
    ac
    0.69
    POSITIVE LOGITS
    것
    0.71
    트는
    0.70
    。
    0.69
    食材
    0.68
    ុង
    0.66
    ズ
    0.63
    集
    0.63
    리는
    0.63
    食
    0.63
    тивных
    0.62
    Activations Density 0.038%

    No Known Activations