© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13619
    Prev
    Next
    INDEX
    Explanations

    words related to a person's profession or accomplishments, often found in sports, politics or entertainment.

    oai_token-act-pair · gemini-2.0-flash

    Public figures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     kaarangay
    -0.66
    makeConstraints
    -0.58
    iastes
    -0.57
    contentLoaded
    -0.57
    ThroughAttribute
    -0.57
     sternum
    -0.56
    InputBorder
    -0.56
    BeginContext
    -0.56
     varandra
    -0.54
    TagMode
    -0.54
    POSITIVE LOGITS
    toLocale
    0.57
    بوابة
    0.54
    Portail
    0.50
    --){
    0.50
     Nevertheless
    0.49
    Nevertheless
    0.48
     useState
    0.48
     заду
    0.47
    lagt
    0.47
    ategorien
    0.46
    Activations Density 1.389%

    No Known Activations