© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10115
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to politics, elections, and government

    oai_token-act-pair · gemini-2.0-flash

    News and code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    hdys
    -0.57
    новништво
    -0.54
    évaluateur
    -0.53
    wegg
    -0.52
     cref
    -0.49
    (!__
    -0.48
    共和
    -0.47
    hot
    -0.47
    Rhestr
    -0.46
    стема
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.69
    पया
    0.63
     AssemblyTitle
    0.62
     상세
    0.62
    basicConfig
    0.61
    MockBean
    0.59
     שוליים
    0.58
    kolwiek
    0.56
    StandardCharsets
    0.56
    참고
    0.55
    Activations Density 2.741%

    No Known Activations