© 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. 34859
    Prev
    Next
    INDEX
    Explanations

    GIMP

    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
     costes
    0.09
     serviço
    0.09
     எச்ச
    0.09
     bov
    0.09
     loke
    0.09
    票房
    0.08
    ϲ
    0.08
     coste
    0.08
     jednotliv
    0.08
     poteva
    0.08
    POSITIVE LOGITS
    ad
    0.11
    يل
    0.10
    יי
    0.09
    NoSuch
    0.09
    "><!--
    0.09
    🖇
    0.09
    тный
    0.09
    ms
    0.09
    '},
    0.09
    сибо
    0.09
    Activations Density 0.015%

    No Known Activations