© 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. 194829
    Prev
    Next
    INDEX
    Explanations

    Stockholm

    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
     ZZ
    0.39
    ెంట్‌
    0.38
    cía
    0.37
    லான
    0.37
    नीय
    0.37
    鏘
    0.37
    Metallic
    0.36
    Ced
    0.36
    prong
    0.35
     %,
    0.35
    POSITIVE LOGITS
    Stock
    2.22
     Stock
    2.08
    stock
    1.98
     stock
    1.94
     STOCK
    1.93
     स्टॉक
    1.85
    STOCK
    1.85
     স্টক
    1.70
     Stockholm
    1.66
     stok
    1.58
    Activations Density 0.003%

    No Known Activations