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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10939
    Prev
    Next
    INDEX
    Explanations

    mentions of a person's debut in sports

    oai_token-act-pair · gemini-2.0-flash

    debut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     debut
    -0.83
    debut
    -0.73
     debuts
    -0.72
     Debut
    -0.65
    paroles
    -0.60
     debuted
    -0.59
    XmlAccessorType
    -0.59
    ene
    -0.59
    ValueStyle
    -0.58
    rasil
    -0.57
    POSITIVE LOGITS
    __':
    0.62
     شد
    0.57
    FetchType
    0.56
    sendRedirect
    0.50
    iastes
    0.50
     attribution
    0.50
    isure
    0.49
    ما
    0.49
    bitat
    0.48
    ActionCreators
    0.48
    Activations Density 3.413%

    No Known Activations