© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9437
    Prev
    Next
    INDEX
    Explanations

    tokens related to debt in Canada, also picking up some numerical tokens

    oai_token-act-pair · gemini-2.0-flash

    Canada

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Canadian
    -2.34
     Canada
    -2.17
    Canadian
    -2.16
     Canadians
    -2.05
    Canada
    -2.05
     CANADIAN
    -1.96
     CANADA
    -1.91
     canadian
    -1.84
     canada
    -1.80
    canadian
    -1.80
    POSITIVE LOGITS
    RegressionTest
    0.55
     Tav
    0.48
     méri
    0.47
    actylus
    0.46
     Spire
    0.45
     Machiavelli
    0.45
    лове
    0.45
     gawas
    0.44
     Señora
    0.44
    atrici
    0.44
    Activations Density 0.893%

    No Known Activations