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

    Neuronpedia

    Jacobian LensNEW
    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. 198715
    Prev
    Next
    INDEX
    Explanations

    IMF, World Bank, GDP

    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
    كينا
    0.41
     wreaths
    0.39
     इट्स
    0.38
    াহীন
    0.38
    pressed
    0.38
    eating
    0.38
    receipt
    0.38
    糯
    0.38
    rát
    0.37
    drawable
    0.37
    POSITIVE LOGITS
     organically
    0.41
     systematically
    0.38
    çons
    0.38
     Меня
    0.37
    CCION
    0.37
    ⿻
    0.37
    פים
    0.35
    dures
    0.35
    กำหนด
    0.35
     MC
    0.34
    Activations Density 0.000%

    No Known Activations