© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14235
    Prev
    Next
    INDEX
    Explanations

    passages that discuss international trade and economics

    oai_token-act-pair · gemini-2.0-flash

    terms related to raw materials and products

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

    materials

    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
     initComponents
    -0.91
    TagMode
    -0.85
    MLLoader
    -0.83
    CloseOperation
    -0.79
    isContained
    -0.77
     تضيفلها
    -0.75
     الرياضيه
    -0.75
    Personendaten
    -0.73
     Exactos
    -0.73
    ValueStyle
    -0.72
    POSITIVE LOGITS
     materials
    0.97
     raw
    0.93
     material
    0.84
     products
    0.84
     goods
    0.82
    raw
    0.78
     resources
    0.78
     items
    0.77
     product
    0.73
    materials
    0.73
    Activations Density 1.446%

    No Known Activations