© 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. 121676
    Prev
    Next
    INDEX
    Explanations

    kiddo/kid / wagon / friendly

    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
    Kid
    0.72
    T
    0.71
     of
    0.65
    L
    0.65
    '
    0.65
    W
    0.65
     fiel
    0.63
    O
    0.62
    Talk
    0.62
    G
    0.62
    POSITIVE LOGITS
    ات
    0.66
    ا
    0.65
    اش
    0.63
    的服务
    0.63
    밂
    0.63
    o
    0.62
    k
    0.62
    لية
    0.62
    kör
    0.62
    на
    0.61
    Activations Density 0.001%

    No Known Activations