© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83888
    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_23_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
     shoved
    0.44
    ofs
    0.44
    ්
    0.43
     gereken
    0.43
    keleton
    0.41
    Conta
    0.41
    ônico
    0.41
     savon
    0.41
     yena
    0.40
     ו
    0.40
    POSITIVE LOGITS
     Hazardous
    0.46
     Fatigue
    0.44
     Firms
    0.43
     August
    0.42
     Victoria
    0.42
     Awards
    0.41
     Patterns
    0.41
     Navigator
    0.41
     Exhaust
    0.41
     Raising
    0.41
    Activations Density 0.000%

    No Known Activations