© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170286
    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_20_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
    loginfo
    0.47
    CORDS
    0.46
     berths
    0.45
    LLING
    0.44
     Chab
    0.44
     الفاظ
    0.43
    께서
    0.43
    ‖</
    0.43
    codes
    0.43
    وفر
    0.41
    POSITIVE LOGITS
    es
    0.48
    Hei
    0.46
     강력
    0.45
     दवाई
    0.43
    ్
    0.43
    श्मीर
    0.42
     alcoholic
    0.41
     Claim
    0.41
     stressful
    0.41
    '.$
    0.41
    Activations Density 0.000%

    No Known Activations