© 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. 38483
    Prev
    Next
    INDEX
    Explanations

    astrocartography, concordance, militarum, force microscopes, atomic heart, astroquery, radius

    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
    ü
    0.92
    ua
    0.86
    ik
    0.86
    на
    0.83
    that
    0.81
    w
    0.77
    не
    0.75
    was
    0.73
    си
    0.70
    <0x0D>
    0.68
    POSITIVE LOGITS
    ed
    0.66
     to
    0.63
    刖
    0.59
    IN
    0.56
    াধিক
    0.56
     as
    0.56
    dig
    0.54
     fury
    0.53
     ceva
    0.53
     Jeden
    0.53
    Activations Density 0.004%

    No Known Activations