© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168049
    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_31_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
     corrige
    0.39
     året
    0.38
     correction
    0.36
     Borges
    0.36
    Corre
    0.35
    теру
    0.34
     दिग्विजय
    0.34
     corrections
    0.33
    აც
    0.33
    趴
    0.33
    POSITIVE LOGITS
    ɭ
    0.38
     ALLOYS
    0.38
     Tobacco
    0.37
     Partially
    0.36
    versal
    0.36
     餐
    0.36
     Vessel
    0.35
    ewall
    0.35
    clusión
    0.35
     feeder
    0.35
    Activations Density 0.000%

    No Known Activations