Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16209
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports teams, specifically soccer, and international competitions

    oai_token-act-pair · gemini-2.0-flash

    National teams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    __*/
    -0.81
    MLLoader
    -0.66
     Roskov
    -0.59
     VIDEOTAPE
    -0.58
     gioielli
    -0.58
    PhysRev
    -0.56
    DispatchToProps
    -0.55
    CppMethod
    -0.55
     SqlParameter
    -0.54
    Carriera
    -0.54
    POSITIVE LOGITS
     national
    1.10
    national
    0.86
     Team
    0.75
     international
    0.72
     National
    0.71
     nacional
    0.68
     selection
    0.67
    NATIONAL
    0.65
     representative
    0.65
     nationale
    0.64
    Activations Density 0.585%

    No Known Activations