© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6707
    Prev
    Next
    INDEX
    Explanations

    capital city

    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_39_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
    resourceUrl
    0.36
     Societies
    0.34
    Despatx
    0.34
    ᓴ
    0.34
     অজ্ঞান
    0.33
     امریکہ
    0.33
     Règles
    0.33
     ("/
    0.32
     здоров
    0.32
     soggiorno
    0.32
    POSITIVE LOGITS
     capital
    0.63
     official
    0.62
    capital
    0.58
    Capital
    0.54
     officially
    0.53
     официа
    0.52
     столи
    0.52
    official
    0.51
     Capital
    0.51
    Official
    0.50
    Activations Density 0.150%

    No Known Activations