© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10402
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to American football

    oai_token-act-pair · gemini-2.0-flash

    Sunday and Super

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    XmlAccessorType
    -0.71
    ActionCreators
    -0.69
    SharedDtor
    -0.68
     Wikimedijinoj
    -0.65
    EnableWeb
    -0.65
    createCanvas
    -0.63
    ThroughAttribute
    -0.63
    SourceChecksum
    -0.63
    parsedMessage
    -0.63
     referenties
    -0.61
    POSITIVE LOGITS
     Sunday
    0.70
    Sunday
    0.65
    SUNDAY
    0.63
     SUNDAY
    0.63
     sunday
    0.54
     Sundays
    0.54
     Super
    0.53
    Super
    0.52
    èlement
    0.49
    tedì
    0.48
    Activations Density 1.332%

    No Known Activations