© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33646
    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_40_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
     item
    0.52
    Item
    0.50
     items
    0.49
     Item
    0.48
     arg
    0.45
     Items
    0.45
     tid
    0.45
    ItemID
    0.45
    春
    0.44
    アイテム
    0.43
    POSITIVE LOGITS
    Upgrade
    0.56
     Upgrade
    0.54
     upgrade
    0.51
    upgrade
    0.51
     upgrading
    0.50
    升级
    0.49
     upgrades
    0.46
     upgraded
    0.44
     Tarifi
    0.43
     وقع
    0.40
    Activations Density 0.025%

    No Known Activations