© 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. 134442
    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
     anticipated
    0.41
    愀
    0.40
    anticipated
    0.38
     ఆడ
    0.38
    antad
    0.37
     chore
    0.36
     ways
    0.33
     সম্বন্ধ
    0.33
     acclaimed
    0.33
     choreographed
    0.33
    POSITIVE LOGITS
    oides
    0.44
    ادف
    0.42
    蹂
    0.41
     geodes
    0.41
    oleum
    0.41
     indígen
    0.40
     nev
    0.40
    ровка
    0.40
    PHAM
    0.39
    देव
    0.38
    Activations Density 0.000%

    No Known Activations