© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199770
    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_27_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
    矨
    0.46
    咶
    0.45
     dalla
    0.45
     modello
    0.44
    िरपेक्ष
    0.44
     גר
    0.43
    lished
    0.43
     aprile
    0.43
     trabal
    0.43
     bhai
    0.42
    POSITIVE LOGITS
    0.44
    rypt
    0.38
    Т
    0.36
    면서
    0.35
     wading
    0.35
    4
    0.34
    Г
    0.33
     Der
    0.33
     Jed
    0.33
     Adequate
    0.33
    Activations Density 0.000%

    No Known Activations