© 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. 211836
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ."
    0.42
     Cortés
    0.41
    कप्तान
    0.41
     inim
    0.39
     .”
    0.38
    𠃌
    0.38
     Jovan
    0.38
     कप्तान
    0.36
     ulaş
    0.36
    ="/"
    0.36
    POSITIVE LOGITS
     Bento
    0.46
    Charset
    0.45
     अनो
    0.44
     दिखाते
    0.43
     Play
    0.43
     tiling
    0.43
     পুনরা
    0.42
     België
    0.42
     firewood
    0.42
     playfully
    0.42
    Activations Density 0.000%

    No Known Activations