© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8245
    Prev
    Next
    INDEX
    Explanations

    words that help define context in sports news, such as prepositions, conjunctions, and determiners

    oai_token-act-pair · gemini-2.0-flash

    football game context

    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
    ::$_
    -0.71
     beginnetje
    -0.66
    LEncoder
    -0.66
    ChildScrollView
    -0.62
    Демографія
    -0.62
     MainAxisSize
    -0.60
    Попис
    -0.59
    parsedMessage
    -0.57
    Chham
    -0.57
    AsUp
    -0.57
    POSITIVE LOGITS
    bkz
    0.47
    ={`/
    0.47
     laiton
    0.47
     feltro
    0.47
    出版年
    0.46
     väli
    0.45
    SequentialGroup
    0.43
     jsPsych
    0.43
     camp
    0.43
    trường
    0.43
    Activations Density 1.451%

    No Known Activations