© 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. 41382
    Prev
    Next
    INDEX
    Explanations

    published dates

    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
    f
    0.62
    ла
    0.61
    inia
    0.61
    N
    0.61
    마다
    0.58
    hous
    0.58
    standard
    0.57
    p
    0.55
    naire
    0.55
    dokka
    0.55
    POSITIVE LOGITS
     February
    0.68
     Sunday
    0.64
     Feb
    0.63
     ရက်
    0.62
     nécessité
    0.60
     necessário
    0.59
     August
    0.59
     Bakery
    0.59
     Física
    0.58
     It
    0.58
    Activations Density 0.001%

    No Known Activations