© 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. 11647
    Prev
    Next
    INDEX
    Explanations

    words and phrases about the United Kingdom and the United States competing

    oai_token-act-pair · 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
     UK
    -2.38
    UK
    -2.16
     British
    -2.09
     £
    -2.05
    British
    -1.96
     (£
    -1.96
     Britain
    -1.91
    Britain
    -1.83
     London
    -1.83
     BRITISH
    -1.78
    POSITIVE LOGITS
    apd
    0.54
    intios
    0.53
    crollView
    0.51
    harapkan
    0.51
     Bioaccumulative
    0.48
    irsch
    0.48
    IFO
    0.47
    vece
    0.47
    tauan
    0.47
     ostavi
    0.47
    Activations Density 2.343%

    No Known Activations