© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34987
    Prev
    Next
    INDEX
    Explanations

    Ajaccio

    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_11_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
    AY
    0.12
    es
    0.11
     доклад
    0.10
     করিম
    0.10
    Ou
    0.10
    ES
    0.10
     sailboats
    0.10
    0
    0.10
    utiérrez
    0.09
     szkol
    0.09
    POSITIVE LOGITS
    מים
    0.09
    );
    0.09
    ק
    0.09
    ंसारी
    0.09
     Bant
    0.09
    पर्स
    0.09
    c
    0.09
     bant
    0.09
    சம்
    0.09
     prion
    0.09
    Activations Density 0.000%

    No Known Activations