© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207810
    Prev
    Next
    INDEX
    Explanations

    drivers

    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_46_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
     flying
    0.46
    flying
    0.39
    Telegram
    0.39
    dokka
    0.38
     Telegram
    0.38
     Flying
    0.37
     பற
    0.37
     ಹ
    0.36
    Flying
    0.36
    ි
    0.36
    POSITIVE LOGITS
     driver
    2.17
     drivers
    2.02
     Driver
    2.02
    driver
    1.95
    Driver
    1.91
     Drivers
    1.84
    Drivers
    1.82
    drivers
    1.79
     ड्राइवर
    1.73
    ドライバー
    1.67
    Activations Density 0.001%

    No Known Activations