© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1092
    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Watt
    0.42
    Twenty
    0.41
    Watt
    0.41
     Equation
    0.41
     watt
    0.40
    荥
    0.39
     zehn
    0.39
    aning
    0.38
     Twenty
    0.38
    River
    0.38
    POSITIVE LOGITS
     밑
    0.43
     underneath
    0.42
     тон
    0.39
     beneath
    0.37
    skyblue
    0.36
    ใต้
    0.36
    ို့
    0.35
     providers
    0.35
    珺
    0.34
    igned
    0.34
    Activations Density 0.008%

    No Known Activations