© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140013
    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_37_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
    底
    0.40
    ьому
    0.39
    WorkingDirectory
    0.38
     partnering
    0.38
     listBox
    0.38
     চক্ষু
    0.37
     imgSrc
    0.37
    Img
    0.36
    底部
    0.36
     پوس
    0.36
    POSITIVE LOGITS
     Colt
    0.40
    ሟ
    0.39
     ပဲ
    0.38
     categorization
    0.37
    ເຄື່ອງ
    0.37
     category
    0.36
     Category
    0.36
     categoria
    0.36
     कैटेगरी
    0.36
     hyperbolic
    0.36
    Activations Density 0.000%

    No Known Activations