© 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. 205183
    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
    Negative Logits
    leven
    0.55
    h
    0.54
    rollup
    0.50
    chemicals
    0.50
     deva
    0.49
    hairs
    0.47
    hā
    0.47
    Denne
    0.47
    heap
    0.47
    fert
    0.46
    POSITIVE LOGITS
    බ
    0.49
    켜
    0.49
     Str
    0.48
     Actions
    0.48
     Auditors
    0.48
     Explor
    0.47
    щая
    0.47
     Military
    0.47
    мая
    0.47
    쨔
    0.46
    Activations Density 0.000%

    No Known Activations