© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54600
    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_31_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
    UART
    0.34
     Advertise
    0.33
     individually
    0.31
     बालक
    0.31
     Individ
    0.31
    牷
    0.31
    Sel
    0.30
     individuelle
    0.30
     individ
    0.30
     sel
    0.30
    POSITIVE LOGITS
    ****",
    0.32
     расход
    0.31
     lights
    0.31
    vič
    0.31
    zęd
    0.30
     "-",
    0.30
     "{
    0.30
     rush
    0.29
    мене
    0.28
    oge
    0.28
    Activations Density 0.000%

    No Known Activations