© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175517
    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recursive
    0.40
    σή
    0.38
     Pohl
    0.38
    
    0.38
     Dray
    0.37
     fibrils
    0.36
    OMI
    0.36
     recursive
    0.35
     وول
    0.35
    ウィ
    0.34
    POSITIVE LOGITS
     ጋ
    0.43
    ម្រ
    0.39
     Gaga
    0.39
    мара
    0.38
     procura
    0.37
    무
    0.37
     Oct
    0.36
    این
    0.36
     concetto
    0.36
    Mac
    0.36
    Activations Density 0.000%

    No Known Activations