© 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. 44980
    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
     boxing
    0.50
    acuda
    0.46
     hippocampus
    0.46
    ytt
    0.45
    ktiv
    0.44
    abella
    0.42
     कार्बन
    0.42
     slags
    0.42
    INFRINGEMENT
    0.42
    區
    0.42
    POSITIVE LOGITS
     effortlessly
    0.52
     את
    0.49
     urgently
    0.45
    utako
    0.45
     لیست
    0.45
    리스
    0.45
     patiently
    0.44
     informée
    0.44
     assess
    0.43
    شاه
    0.42
    Activations Density 0.000%

    No Known Activations