© 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. 51791
    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
     évolution
    0.49
     বিলম্ব
    0.46
     événements
    0.46
     ornare
    0.45
    时期
    0.45
     possèdent
    0.45
     particulates
    0.44
     时尚
    0.44
     চুম্বন
    0.44
    }($
    0.43
    POSITIVE LOGITS
     seven
    0.54
    an
    0.50
    Prove
    0.50
     OF
    0.49
    en
    0.49
    There
    0.48
    in
    0.47
     It
    0.46
    AL
    0.46
     five
    0.46
    Activations Density 0.000%

    No Known Activations