© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149659
    Prev
    Next
    INDEX
    Explanations

    race or other

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     race
    2.42
     Race
    2.20
    race
    2.16
    Race
    2.16
    赛
    1.91
     RACE
    1.77
    賽
    1.70
     races
    1.32
     Races
    1.20
    レース
    1.20
    POSITIVE LOGITS
    Scheme
    0.34
    lemon
    0.34
    𝑯
    0.34
    功夫
    0.33
    хема
    0.32
     esquema
    0.32
     அப்படியே
    0.31
    pture
    0.31
    algorithm
    0.31
    Kelly
    0.31
    Activations Density 0.001%

    No Known Activations