© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81314
    Prev
    Next
    INDEX
    Explanations

    code and imports

    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_31_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
     Hewitt
    0.38
     Howell
    0.38
     Pon
    0.38
     Nixon
    0.38
     Simmons
    0.38
    -)
    0.37
     Badajoz
    0.37
    ওয়
    0.37
    Pon
    0.37
    尾
    0.37
    POSITIVE LOGITS
    𝖒
    0.41
    মেয়ে
    0.37
     common
    0.36
     आम
    0.36
     elites
    0.36
     чыныгы
    0.35
    স্থিত
    0.35
     democratization
    0.35
     dítě
    0.35
    झ्
    0.35
    Activations Density 0.001%

    No Known Activations