© 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. 143639
    Prev
    Next
    INDEX
    Explanations

    forces

    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
     Evo
    0.41
     ROY
    0.40
    ppy
    0.39
    計画
    0.39
     command
    0.39
    ត
    0.39
     evac
    0.38
    opilot
    0.38
     quiet
    0.37
     Training
    0.37
    POSITIVE LOGITS
    鍾
    0.46
    泼
    0.40
     சுண்ணாம்பு
    0.40
     बृ
    0.39
    ಟರ್
    0.38
     ର
    0.38
    Enders
    0.38
    Kunst
    0.38
     Lebensmittel
    0.38
    ులు
    0.37
    Activations Density 0.001%

    No Known Activations