© 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. 134342
    Prev
    Next
    INDEX
    Explanations

    q

    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
    㣱
    0.38
     пер
    0.37
     interi
    0.37
    setPreferred
    0.36
    եցին
    0.36
    zaXR
    0.35
    COS
    0.34
     Тере
    0.34
    Bel
    0.34
    䉽
    0.34
    POSITIVE LOGITS
    च्च
    0.44
    ニーカー
    0.41
    岭
    0.39
     корне
    0.39
    リン
    0.39
    busch
    0.38
    悅
    0.38
     dominante
    0.38
     Lincoln
    0.37
     dangerously
    0.37
    Activations Density 0.001%

    No Known Activations