© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67731
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
    出し
    0.36
    NDE
    0.36
    impan
    0.36
    istasis
    0.35
     экспери
    0.35
    状况
    0.35
    ܡܪ
    0.35
    isie
    0.34
    )$$
    0.34
    zust
    0.34
    POSITIVE LOGITS
     private
    1.23
    Private
    1.17
     Private
    1.13
     PRIVATE
    1.05
    private
    1.02
    私
    0.99
    PRIVATE
    0.95
     निजी
    0.95
     privata
    0.94
     privato
    0.93
    Activations Density 0.000%

    No Known Activations