© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13162
    Prev
    Next
    INDEX
    Explanations

    the word "Product" and related terms such as "part" and "information"

    oai_token-act-pair · gemini-2.0-flash

    technical product terminology

    np_token-act-pair-logits · gpt-4o-mini

    Product

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    graphique
    -0.45
    Trama
    -0.44
    com
    -0.43
    Jäh
    -0.43
     کیلومتر
    -0.42
    class
    -0.42
     menye
    -0.40
     pre
    -0.40
    org
    -0.39
    pre
    -0.39
    POSITIVE LOGITS
    Autoritní
    0.90
    WebVitals
    0.83
    RenderAtEndOf
    0.81
     <=",
    0.73
    InjectAttribute
    0.73
     EconPapers
    0.73
    ReusableCell
    0.70
     initComponents
    0.69
    ronpa
    0.69
    findpost
    0.68
    Activations Density 0.167%

    No Known Activations