© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 103363
    Prev
    Next
    INDEX
    Explanations

    American, Asian people

    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_16_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
    iffer
    0.47
    ervation
    0.46
     Roller
    0.46
    köy
    0.45
    /
    0.45
    頑
    0.45
    ilience
    0.45
    远
    0.44
    encies
    0.44
    ü
    0.43
    POSITIVE LOGITS
     creativo
    0.54
     financieras
    0.54
    ತ್ರ
    0.53
     complesso
    0.52
     izinsuku
    0.52
    ໄຂ
    0.52
     시즌
    0.49
     これらの
    0.49
    黐
    0.48
     oito
    0.47
    Activations Density 0.000%

    No Known Activations