© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11546
    Prev
    Next
    INDEX
    Explanations

    mentions of a "Burpee" fitness challenge.

    oai_token-act-pair · gemini-2.0-flash

    Exercise or code

    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
    ionView
    -0.55
     tait
    -0.51
     dok
    -0.51
     contamination
    -0.50
    spill
    -0.49
     expon
    -0.48
    artifact
    -0.47
     Notícias
    -0.47
     matrícula
    -0.47
     MDL
    -0.46
    POSITIVE LOGITS
    mybatisplus
    0.76
    новниш
    0.65
     @"/
    0.64
     AssemblyCulture
    0.63
     Italijani
    0.63
    IsMutable
    0.61
    цезда
    0.60
    parsedMessage
    0.59
     Italijanski
    0.56
     resourceCulture
    0.56
    Activations Density 0.213%

    No Known Activations