© 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. 194635
    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
    Negative Logits
    iments
    0.45
    BOX
    0.42
    ALK
    0.42
    DRO
    0.41
    לט
    0.41
    DAVID
    0.41
     مض
    0.41
    iment
    0.40
    
    0.40
     Prix
    0.40
    POSITIVE LOGITS
     Monica
    0.43
     pasting
    0.41
     Monterey
    0.40
    María
    0.40
     HashSet
    0.39
     کری
    0.38
     Katherine
    0.38
     মনি
    0.37
     clapping
    0.37
     monomer
    0.37
    Activations Density 0.000%

    No Known Activations