Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14708
    Prev
    Next
    INDEX
    Explanations

    statistics and outcome phrases in baseball and football reports

    oai_token-act-pair · gemini-2.0-flash

    Sports winning/losing

    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
     calendriers
    -0.57
     AppCompatTheme
    -0.47
     succession
    -0.46
     Latest
    -0.45
    handleRequest
    -0.45
     videa
    -0.45
    理石
    -0.45
    Attached
    -0.44
    از
    -0.43
    Latest
    -0.42
    POSITIVE LOGITS
     AttributeSet
    0.63
     BoxFit
    0.61
    ToBounds
    0.60
    جمعیت
    0.57
     []),
    0.53
    ∬
    0.52
    Hentet
    0.52
    ุม
    0.51
     allmän
    0.50
    ulemon
    0.49
    Activations Density 0.871%

    No Known Activations