© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209539
    Prev
    Next
    INDEX
    Explanations

    country names, geography

    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_19_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
    Request
    0.47
     harbor
    0.46
    ।
    0.45
     harbour
    0.44
     উদ্যোগ
    0.44
    ذية
    0.43
     coercion
    0.43
     هنگام
    0.43
     Harbor
    0.43
    ک
    0.42
    POSITIVE LOGITS
     Grèce
    0.52
     españa
    0.50
    swf
    0.50
     Polska
    0.50
     colombiano
    0.50
     Españ
    0.49
     Sempre
    0.49
     Subhanahu
    0.46
     मोनो
    0.46
    GLuint
    0.46
    Activations Density 0.001%

    No Known Activations