© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45130
    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_10_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
    cribable
    0.55
     व्यक्त
    0.51
    turbulence
    0.48
     مختلف
    0.47
    มาตรฐาน
    0.46
    ،
    0.46
    
    0.46
     عالی
    0.45
    कोष्ठ
    0.45
    uiDesigner
    0.44
    POSITIVE LOGITS
     Serb
    0.56
    is
    0.55
     ends
    0.50
     I
    0.49
     Deci
    0.48
     Serr
    0.47
     Ends
    0.47
    Ķ
    0.47
     Lanes
    0.47
     Well
    0.47
    Activations Density 0.000%

    No Known Activations