© 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. 226831
    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
    е
    0.70
     Barcelona
    0.55
     با
    0.53
    de
    0.51
     pour
    0.51
    ın
    0.51
     CBR
    0.50
     с
    0.49
     Geological
    0.49
     Now
    0.49
    POSITIVE LOGITS
    シャレ
    0.46
     signaled
    0.45
     catalyzes
    0.45
     initializes
    0.45
    itaea
    0.44
    >`;
    0.43
     rhenium
    0.43
    사에
    0.42
     dogged
    0.42
    
    0.42
    Activations Density 0.000%

    No Known Activations