© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238680
    Prev
    Next
    INDEX
    Explanations

    driver or guide roles

    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_32_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
     evenings
    0.39
     enjoys
    0.39
    Robert
    0.39
     evening
    0.37
     greets
    0.37
    evi
    0.36
    夜
    0.35
    Mr
    0.35
     Pad
    0.35
     pad
    0.34
    POSITIVE LOGITS
     οδηγ
    0.49
    drivers
    0.42
    司机
    0.42
     conducteur
    0.40
     मालिनी
    0.39
     driver
    0.39
    driver
    0.38
     begele
    0.38
     drivers
    0.38
    neut
    0.38
    Activations Density 0.000%

    No Known Activations