© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129107
    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_1_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
     WERE
    1.00
    เรา
    0.98
    1
    0.98
    </strong>
    0.97
    ;
    0.93
    </b>
    0.92
    и
    0.89
     pela
    0.89
     cuales
    0.87
     которые
    0.86
    POSITIVE LOGITS
    ed
    1.04
    B
    1.00
    L
    0.98
    W
    0.98
    ad
    0.93
    H
    0.91
    కు
    0.91
    J
    0.89
    पणे
    0.88
    toare
    0.88
    Activations Density 0.000%

    No Known Activations