© 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. 8574
    Prev
    Next
    INDEX
    Explanations

    relatable

    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
    Ⲗ
    0.13
    Cliente
    0.13
    diabetes
    0.13
    üsseldorf
    0.12
    Sunglasses
    0.12
    |=\
    0.12
    connecting
    0.12
    Naive
    0.12
    kę
    0.12
    Iceland
    0.12
    POSITIVE LOGITS
     botched
    0.11
     Farrar
    0.10
    izan
    0.10
     Warrant
    0.10
     reckons
    0.10
    <0x8B>
    0.10
     War
    0.10
     mı
    0.10
     didn
    0.10
     wasn
    0.10
    Activations Density 0.046%

    No Known Activations