© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54834
    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_30_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
     разви
    0.41
     ذریع
    0.40
    width
    0.38
    加热
    0.38
     قلنا
    0.37
    calup
    0.37
    ayın
    0.36
    ინის
    0.36
    dimensioni
    0.36
     ގ
    0.35
    POSITIVE LOGITS
     authorizes
    0.41
     smother
    0.40
     struck
    0.39
    QR
    0.39
     permitted
    0.38
     permits
    0.38
     account
    0.38
    Account
    0.38
     destruction
    0.38
     wedge
    0.38
    Activations Density 0.000%

    No Known Activations