© 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. 10442
    Prev
    Next
    INDEX
    Explanations

    tokens that participate in sports, especially the names of sports leagues and tournaments

    oai_token-act-pair · gemini-2.0-flash

    Sports and competitions

    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
    clero
    -0.52
    rents
    -0.49
    IPAC
    -0.48
     Damp
    -0.48
     chłod
    -0.47
     regist
    -0.46
    BY
    -0.45
     artysty
    -0.44
    ின்ற
    -0.44
    ggia
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.95
    webElementXpaths
    0.70
    évaluateur
    0.65
    ModelSerializer
    0.63
    WriteAttribute
    0.62
     Wiktionnaire
    0.60
    GOTREF
    0.60
     continúas
    0.57
    AddTagHelper
    0.56
    writeField
    0.56
    Activations Density 0.503%

    No Known Activations