© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154477
    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_23_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
    ao
    0.45
    one
    0.44
     antimicrobial
    0.44
    NO
    0.44
     global
    0.43
     attribute
    0.43
     trip
    0.43
     Author
    0.42
     &
    0.42
    ↵
    0.42
    POSITIVE LOGITS
     fortr
    0.52
    нных
    0.51
     режиме
    0.50
    स्वा
    0.49
     kroppen
    0.48
    ндо
    0.48
    几种
    0.48
    粔
    0.48
     संस्थानों
    0.47
    বাই
    0.47
    Activations Density 0.000%

    No Known Activations