© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89308
    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_60_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
     Și
    0.60
     Center
    0.54
     അവൻ
    0.52
    Center
    0.49
     Ș
    0.49
     față
    0.49
    țional
    0.48
     și
    0.47
     ഇപ്പോൾ
    0.47
     creș
    0.46
    POSITIVE LOGITS
     to
    0.64
     as
    0.57
     for
    0.53
    to
    0.52
     that
    0.44
     is
    0.43
    :");
    0.42
    :";
    0.41
     دیتے
    0.41
     advised
    0.41
    Activations Density 0.000%

    No Known Activations