© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10908
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly found in academic publications, especially in mathematics, statistics, and computer science

    oai_token-act-pair · gemini-2.0-flash

    computer science, math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    MethodManager
    -0.47
     Ammonia
    -0.47
    domésticos
    -0.46
     décé
    -0.45
    ServiceException
    -0.45
    qtype
    -0.44
     Implemented
    -0.44
     involunt
    -0.43
     répondit
    -0.43
     souple
    -0.43
    POSITIVE LOGITS
    parsedMessage
    0.69
     gawas
    0.68
    -------------</
    0.65
    yeezy
    0.63
    WebElementEntity
    0.62
     <<<<<<<<<<<<<<
    0.61
    -------
    0.60
    ulco
    0.59
    lhes
    0.57
    closedir
    0.57
    Activations Density 25.814%

    No Known Activations