© 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. 9690
    Prev
    Next
    INDEX
    Explanations

    words related to politics, especially when discussing what "people" think.

    oai_token-act-pair · gemini-2.0-flash

    nationality or demographic identifiers

    np_token-act-pair-logits · gpt-4o-mini

    countries / nationalities

    np_max-act-logits · gemini-2.0-flash
    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
     الحره
    -0.69
     Magnetism
    -0.62
     кӀ
    -0.59
     Púb
    -0.58
     élector
    -0.57
     Paro
    -0.57
    ✭✭
    -0.56
     deſt
    -0.56
    QMetaType
    -0.56
     Anſ
    -0.56
    POSITIVE LOGITS
     Americans
    1.27
    Americans
    1.05
     Canadians
    1.02
     Califor
    1.01
     Australians
    1.01
     American
    0.92
     Nigerians
    0.91
     Kenyans
    0.90
    Aust
    0.87
     Texans
    0.82
    Activations Density 1.760%

    No Known Activations