© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43482
    Prev
    Next
    INDEX
    Explanations

    lord, lady, company, church

    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
    For
    0.78
    (
    0.75
    <
    0.74
    >
    0.70
    AL
    0.69
    OD
    0.67
    +
    0.66
    In
    0.65
     For
    0.64
    ně
    0.64
    POSITIVE LOGITS
     is
    0.78
     Вайлд
    0.65
    си
    0.64
    влека
    0.64
    an
    0.64
     ethos
    0.64
    imethyl
    0.63
    ા
    0.63
    ان
    0.62
    ！)
    0.62
    Activations Density 0.001%

    No Known Activations