© 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. 9970
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to government and politics

    oai_token-act-pair · gemini-2.0-flash

    committee

    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
    DoubleQuotes
    -0.63
    aranja
    -0.63
    ppins
    -0.57
    ImageField
    -0.55
     bVar
    -0.54
    aderie
    -0.51
    hagic
    -0.50
    equalTo
    -0.49
    tyard
    -0.49
    σκ
    -0.49
    POSITIVE LOGITS
     parliamentary
    0.83
     Parliament
    0.77
     parlamentar
    0.75
     parliament
    0.73
     Parliamentary
    0.73
     Houſe
    0.69
     Parlament
    0.69
    Parliament
    0.68
     congressional
    0.68
    parliament
    0.68
    Activations Density 1.480%

    No Known Activations