© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154513
    Prev
    Next
    INDEX
    Explanations

    technical context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     bono
    0.47
     bont
    0.46
     Bono
    0.42
     втра
    0.42
     Gar
    0.40
    Bond
    0.40
     Бон
    0.40
     Bik
    0.39
    皂
    0.39
    苙
    0.39
    POSITIVE LOGITS
    ComponentName
    0.46
    <unused22>
    0.41
     P
    0.38
     Canal
    0.38
     ArrayIndex
    0.38
     Jorg
    0.37
    ではない
    0.36
     પગ
    0.36
    ]|[
    0.35
     chang
    0.35
    Activations Density 0.000%

    No Known Activations