© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2826
    Prev
    Next
    INDEX
    Explanations

    words associated with teams, and countries

    oai_token-act-pair · gemini-2.0-flash

    Angolan sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.95
    </caption>
    -0.79
    AddHtmlAttribute
    -0.79
    __':
    -0.78
     disambiguazione
    -0.77
    tagHelperRunner
    -0.74
    Autoritní
    -0.73
     שוליים
    -0.72
    ніципалі
    -0.72
    Personensuche
    -0.71
    POSITIVE LOGITS
     Portugal
    0.60
    Portugal
    0.56
    Bissau
    0.49
     Jameson
    0.47
    ostomy
    0.47
     Fag
    0.47
     Mac
    0.47
    leon
    0.46
     ven
    0.45
    criminate
    0.45
    Activations Density 2.329%

    No Known Activations