© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102784
    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_14_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
     elasticity
    0.69
     exogenous
    0.60
     melted
    0.59
     იყ
    0.57
     merger
    0.56
     лицен
    0.56
     мета
    0.55
     обла
    0.55
     inflamed
    0.55
     ಖ
    0.54
    POSITIVE LOGITS
    2
    0.59
    Introducing
    0.56
    8
    0.56
    Giving
    0.55
    id
    0.54
    打
    0.54
    Increasing
    0.53
    T
    0.53
    type
    0.52
    Oct
    0.52
    Activations Density 0.000%

    No Known Activations