© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1342
    Prev
    Next
    INDEX
    Explanations

    mentions of political processes and government entities.

    oai_token-act-pair · gemini-2.0-flash

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     government
    -2.22
     Government
    -2.14
    Government
    -2.13
    government
    -1.95
     GOVERNMENT
    -1.84
    GOVERNMENT
    -1.73
     Govt
    -1.55
    政府
    -1.51
     governments
    -1.46
    Govt
    -1.44
    POSITIVE LOGITS
    DeleteBehavior
    0.67
    writeFieldEnd
    0.66
    LayoutStyle
    0.65
    MLLoader
    0.64
     Exactos
    0.63
    fromnode
    0.62
     disambiguazione
    0.62
    ParallelGroup
    0.61
    HomeAsUpEnabled
    0.61
     EconPapers
    0.60
    Activations Density 8.877%

    No Known Activations