© 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. 206769
    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
    pperm
    0.40
     Dolomites
    0.39
    oglou
    0.38
     smelt
    0.38
     laranja
    0.38
     psia
    0.38
    ulos
    0.38
    謢
    0.38
     gó
    0.37
     passed
    0.37
    POSITIVE LOGITS
     chu
    0.40
     Markdown
    0.38
     tvor
    0.37
     markdown
    0.35
    朦
    0.35
     Thế
    0.34
    Cartoon
    0.34
    测评
    0.34
     lines
    0.33
    之为
    0.33
    Activations Density 0.000%

    No Known Activations