© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121621
    Prev
    Next
    INDEX
    Explanations

    hot glue, Ho Ho Ho, hot wired, hot rods, yoga

    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
    Negative Logits
    '
    0.91
    -
    0.81
    $.
    0.71
    ür
    0.71
    edges
    0.69
     сложности
    0.68
    bait
    0.66
     proie
    0.66
     manquer
    0.65
    $+
    0.63
    POSITIVE LOGITS
    ח
    1.14
    ש
    0.86
    ן
    0.68
     በጣም
    0.66
    ต
    0.65
    is
    0.64
    ین
    0.64
    та
    0.63
    り
    0.62
    ִ
    0.61
    Activations Density 0.001%

    No Known Activations