© 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. 62757
    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
    Freq
    0.47
    Tras
    0.46
     Andree
    0.46
    Distance
    0.46
     encapsulates
    0.45
     दूं
    0.45
    ట్‌లో
    0.45
    Ꮞ
    0.45
    FPS
    0.45
    રિક
    0.44
    POSITIVE LOGITS
    r
    0.60
    il
    0.57
     belief
    0.53
    l
    0.53
    belief
    0.49
     ве
    0.49
     elementi
    0.48
     regime
    0.48
    ิ
    0.48
    로서
    0.48
    Activations Density 0.000%

    No Known Activations