© 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. 175388
    Prev
    Next
    INDEX
    Explanations

    S

    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
    vao
    0.40
    굶
    0.40
    ۱۹
    0.40
     BEL
    0.38
    enol
    0.38
    মেন
    0.38
    ENO
    0.37
    Tw
    0.37
    eliers
    0.37
     ഭാ
    0.37
    POSITIVE LOGITS
    >≤</
    0.46
    тке
    0.40
    ply
    0.40
     dale
    0.40
    त्कार
    0.39
     ply
    0.38
     найд
    0.38
    сии
    0.38
     quartile
    0.38
    ادات
    0.37
    Activations Density 0.002%

    No Known Activations