© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30286
    Prev
    Next
    INDEX
    Explanations

    Why it matters:

    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_10_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
     était
    0.18
     Lupus
    0.17
    ールの
    0.17
     河
    0.17
    ována
    0.16
    </b>
    0.16
     Femme
    0.16
    주시
    0.16
    يكي
    0.15
     Société
    0.15
    POSITIVE LOGITS
    ):
    0.22
    0
    0.21
     homomorphism
    0.20
    р
    0.20
     उदाहरण
    0.18
    ));
    0.18
    σ
    0.18
    मा
    0.18
     Canadi
    0.17
    B
    0.17
    Activations Density 0.063%

    No Known Activations