© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 719
    Prev
    Next
    INDEX
    Explanations

    quotes and mentions of sports teams, specifically in the context of soccer/football, along with related terms such as "manager", "academy", and "youth team."

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    ">//
    -0.72
    She
    -0.69
    ագրություններ
    -0.67
     Women
    -0.64
     She
    -0.61
    Women
    -0.59
     Girls
    -0.59
    ViewImports
    -0.59
    __":
    -0.59
    QMetaType
    -0.59
    POSITIVE LOGITS
    EndContext
    0.59
     Advantage
    0.57
    RegistryLite
    0.52
    ScopeManager
    0.52
     Nagasaki
    0.47
     Agamemnon
    0.47
    readystatechange
    0.47
    Upgradeable
    0.45
     Pender
    0.45
    ValueStyle
    0.44
    Activations Density 13.546%

    No Known Activations