© 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. 12931
    Prev
    Next
    INDEX
    Explanations

    school and sports related terms

    oai_token-act-pair · gemini-2.0-flash

    School subjects and sports

    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
    <bos>
    -0.66
    ︎
    -0.65
     HasFactory
    -0.63
    endphp
    -0.61
    yarnpkg
    -0.60
     ExecuteAsync
    -0.60
    yorsunuz
    -0.59
     Paglinawan
    -0.55
    SharedCtor
    -0.55
     régle
    -0.54
    POSITIVE LOGITS
     AssemblyProduct
    0.59
     handball
    0.50
    othermal
    0.50
     undercover
    0.48
     sev
    0.48
     enfer
    0.46
    Související
    0.46
    cellaneous
    0.46
    /'
    0.45
    ekwondo
    0.45
    Activations Density 0.720%

    No Known Activations