© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8786
    Prev
    Next
    INDEX
    Explanations

    edge cases and season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    ě
    0.48
    ст
    0.46
     *$
    0.46
    iddag
    0.46
     <
    0.45
     cellules
    0.44
    ocellular
    0.43
    с
    0.43
    寳
    0.43
     *
    0.43
    POSITIVE LOGITS
    但他
    0.55
    зел
    0.50
     banane
    0.49
     but
    0.48
     reinsurance
    0.48
     संभावना
    0.48
     seti
    0.47
     Marsh
    0.47
    iraju
    0.47
     concili
    0.47
    Activations Density 0.078%

    No Known Activations