© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12575
    Prev
    Next
    INDEX
    Explanations

    things related to the United States, especially in the context of international relations and trade

    oai_token-act-pair · gemini-2.0-flash

    United States/U

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     US
    -2.20
    US
    -1.91
     USA
    -1.81
    USA
    -1.58
     Usa
    -1.34
     usa
    -1.30
     UK
    -1.29
    usa
    -1.14
     Us
    -1.09
    Usa
    -1.07
    POSITIVE LOGITS
    U
    0.78
     U
    0.69
    u
    0.66
     u
    0.50
    )}}{
    0.47
    úť
    0.46
    ייה
    0.46
     zod
    0.44
    runde
    0.44
    Sullivan
    0.43
    Activations Density 5.353%

    No Known Activations