© 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. 154411
    Prev
    Next
    INDEX
    Explanations

    technical/foreign symbols

    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
     высо
    0.64
     висо
    0.54
     hoog
    0.54
    高
    0.52
     høy
    0.52
     alto
    0.50
     High
    0.50
    высо
    0.49
     Vysok
    0.49
     höheren
    0.48
    POSITIVE LOGITS
     কীর
    0.41
    Prepar
    0.39
    Ư
    0.35
    textbf
    0.35
     އަ
    0.35
    izzard
    0.34
    Adap
    0.34
    িতে
    0.33
     विष
    0.33
    ネタ
    0.33
    Activations Density 0.000%

    No Known Activations