© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220577
    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_10_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
    𒌓
    0.49
     удосто
    0.44
     coalesce
    0.43
    山市
    0.42
    inati
    0.42
    vanishing
    0.42
     assignee
    0.42
     위한
    0.41
    서울특별시
    0.41
     provincia
    0.41
    POSITIVE LOGITS
     hot
    0.52
     hoga
    0.52
    </h4>
    0.51
    </h3>
    0.50
    awsze
    0.47
     Buddhism
    0.46
    <sup>
    0.46
    azines
    0.46
     zou
    0.46
     HOT
    0.46
    Activations Density 0.000%

    No Known Activations