© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155821
    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_60_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
    0
    0.45
    aging
    0.38
    Colour
    0.38
     Clk
    0.38
    rock
    0.38
    ţiei
    0.37
     Ouais
    0.37
    ager
    0.36
    uuml
    0.36
     Btn
    0.36
    POSITIVE LOGITS
     ―
    0.40
    ябрь
    0.38
     figura
    0.38
     practice
    0.37
     absol
    0.37
     case
    0.36
     figure
    0.36
     código
    0.36
     not
    0.35
     janeiro
    0.35
    Activations Density 0.000%

    No Known Activations