© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24090
    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_10_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
     profesores
    0.62
    бо
    0.55
     cálculos
    0.52
     pessoas
    0.52
     daca
    0.51
     procesos
    0.51
    úd
    0.51
     quienes
    0.50
    보
    0.50
     comerciantes
    0.50
    POSITIVE LOGITS
     Wages
    0.49
    ต่อไป
    0.48
     λεπ
    0.47
     forfeiture
    0.45
     Theft
    0.44
    )`;
    0.44
    𝓉
    0.43
     NIR
    0.43
    执行
    0.42
    退
    0.42
    Activations Density 0.000%

    No Known Activations