© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157367
    Prev
    Next
    INDEX
    Explanations

    Kuala Lumpur

    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
    Not in Any Lists

    No Comments

    Negative Logits
    utable
    0.41
    K
    0.41
    の結果
    0.39
    仁
    0.38
     ಖ
    0.37
     কৰি
    0.36
     करू
    0.36
    控股
    0.36
     nád
    0.36
    kWh
    0.35
    POSITIVE LOGITS
     Duma
    0.41
    doped
    0.40
    㽛
    0.40
     buffered
    0.39
    وریت
    0.39
     Regime
    0.38
     Baird
    0.38
     Eliot
    0.38
     bach
    0.38
    orphisms
    0.36
    Activations Density 0.000%

    No Known Activations