© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62734
    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_11_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
     ));
    0.52
    há
    0.50
     abundances
    0.50
    Biblioteca
    0.49
     tego
    0.49
     წ
    0.48
     ').
    0.47
    alkoz
    0.47
    Parrocchia
    0.47
     côte
    0.46
    POSITIVE LOGITS
    耕
    0.47
    と考え
    0.46
    クマ
    0.45
    春
    0.44
    standard
    0.43
    Intensity
    0.43
     moj
    0.43
    ーリー
    0.43
    SetStr
    0.43
    spring
    0.42
    Activations Density 0.000%

    No Known Activations