© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15168
    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_13_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
    celona
    0.49
     विपरीत
    0.47
    Social
    0.47
    steil
    0.47
    Promo
    0.46
    Bill
    0.45
    B
    0.45
    Subject
    0.45
     Opposition
    0.45
    Mount
    0.45
    POSITIVE LOGITS
    나
    0.53
     kh
    0.49
    ಿವೆ
    0.48
     girder
    0.48
     codewords
    0.48
    지
    0.48
     favicon
    0.48
     pact
    0.47
    да
    0.47
     wody
    0.47
    Activations Density 0.000%

    No Known Activations