© 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. 7045
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to the United States, international politics, and dates

    oai_token-act-pair · gemini-2.0-flash

    keywords related to international trade agreements

    np_token-act-pair-logits · gpt-4o-mini
    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
    )&&(
    -0.50
     Pembangunan
    -0.48
    InputBorder
    -0.47
    bronn
    -0.46
     bewe
    -0.46
    WebMethod
    -0.46
    perties
    -0.46
     onCancelled
    -0.46
    DataSnapshot
    -0.45
    HasOne
    -0.45
    POSITIVE LOGITS
     disambiguazione
    0.85
    Rounds
    0.58
    devamını
    0.50
    Doha
    0.50
    rungsseite
    0.50
    ViewImports
    0.50
     Doha
    0.49
    Opening
    0.49
    diers
    0.48
     مرئيه
    0.47
    Activations Density 1.477%

    No Known Activations