© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6021
    Prev
    Next
    INDEX
    Explanations

    capital cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    routers
    0.38
     geng
    0.38
    蒽
    0.38
     फुलकारी
    0.37
    Newman
    0.37
    နယ်
    0.36
    rét
    0.36
    Се
    0.36
    Baxter
    0.36
    ሊ
    0.36
    POSITIVE LOGITS
     capital
    0.57
     capitals
    0.56
    capital
    0.49
     столи
    0.48
     Capital
    0.47
     CAPITAL
    0.47
    capitalize
    0.46
     Capitals
    0.45
    Capital
    0.44
     Hauptstadt
    0.43
    Activations Density 0.045%

    No Known Activations