© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206911
    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_6_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
    ೂರ್
    0.92
    闿
    0.89
     Mahatma
    0.88
     ʼ
    0.87
    Ꮅ
    0.87
     shimmering
    0.86
     ʻ
    0.84
     Bhutan
    0.83
     Zuid
    0.83
    ದಲ್ಲಿ
    0.83
    POSITIVE LOGITS
    -
    1.88
    s
    1.34
    0
    1.16
    es
    1.14
    ),
    1.13
    ’
    1.13
    ↵↵
    1.05
    ant
    1.05
    .
    1.03
    <start_of_image>
    1.03
    Activations Density 0.000%

    No Known Activations