© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199738
    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_27_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
    繕
    0.42
    pai
    0.38
     antider
    0.37
     ondernem
    0.37
    而非
    0.37
    albeit
    0.35
    委员
    0.35
     hepinize
    0.35
    綪
    0.34
    paren
    0.34
    POSITIVE LOGITS
    Correction
    0.42
     침
    0.39
     другую
    0.39
     Quiet
    0.38
     Tour
    0.38
     सें
    0.36
     бази
    0.35
    Tue
    0.35
     Visitation
    0.35
    Teller
    0.35
    Activations Density 0.000%

    No Known Activations