© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13748
    Prev
    Next
    INDEX
    Explanations

    reports of football games including player names, team names, and football terminology, and numbers representing scores and times

    oai_token-act-pair · gemini-2.0-flash

    football games

    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
    +:+
    -0.69
    ConstraintMaker
    -0.67
     estekak
    -0.67
    oredCriteria
    -0.64
     limestone
    -0.63
     متعلقه
    -0.62
    +#+#
    -0.62
     getopt
    -0.60
     impunity
    -0.59
    تقاوى
    -0.59
    POSITIVE LOGITS
    зулта
    0.56
     חיצוניים
    0.46
     scel
    0.44
     consommation
    0.42
     ordres
    0.41
    Rüyada
    0.40
    állítás
    0.40
    STORAGE
    0.40
    XmlRootElement
    0.38
     numberOfRows
    0.38
    Activations Density 0.479%

    No Known Activations