© 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. 4145
    Prev
    Next
    INDEX
    Explanations

    mentions of US politicians and political bodies

    oai_token-act-pair · gemini-2.0-flash

    senate

    np_max-act · gemini-2.0-flash

    Senator

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ymce
    -0.53
     Pelt
    -0.50
     оригіналу
    -0.49
    iksa
    -0.49
    __':
    -0.49
    tacular
    -0.48
    جاب
    -0.48
    rijfs
    -0.47
    ingtones
    -0.47
    __':
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.80
     senator
    0.77
     senators
    0.77
    Senator
    0.76
     Senator
    0.72
    клопе
    0.68
     Senators
    0.68
     springfox
    0.63
    setVerticalGroup
    0.62
    CloseOperation
    0.60
    Activations Density 1.040%

    No Known Activations