© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143676
    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_46_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
    Apache
    0.39
     Placeholder
    0.36
    unic
    0.36
    Placeholder
    0.36
    conect
    0.35
    placeholder
    0.35
     placeholder
    0.34
    🚀
    0.34
    ок
    0.33
     Poor
    0.33
    POSITIVE LOGITS
     neighbor
    0.61
     Neighbors
    0.61
     Neighbor
    0.60
     neighbors
    0.60
     Neigh
    0.58
    Neighbor
    0.57
     neighbours
    0.56
     neighbour
    0.56
    neighbors
    0.54
    Neighbors
    0.53
    Activations Density 0.000%

    No Known Activations