© 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. 91983
    Prev
    Next
    INDEX
    Explanations

    blue moon, prism, jackets

    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
     hermoso
    0.59
    สวย
    0.59
    ล
    0.56
    ны
    0.55
    ro
    0.54
    漂亮的
    0.54
    OLF
    0.53
    னு
    0.52
    ark
    0.51
     Yolanda
    0.51
    POSITIVE LOGITS
     of
    0.71
    که
    0.69
    modation
    0.67
    讯
    0.66
    ิล
    0.66
     discretization
    0.66
    ヤモンド
    0.65
    филлер
    0.65
    oną
    0.64
     sensitization
    0.64
    Activations Density 0.001%

    No Known Activations