© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3435
    Prev
    Next
    INDEX
    Explanations

    capital-letter abbreviations for official-sounding organizations or locations and titles for people.

    oai_token-act-pair · gemini-2.0-flash

    terms related to the UK and London

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

    Location: London, UK

    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
     coleg
    -0.54
     كره
    -0.49
    Hentet
    -0.49
    Scripting
    -0.47
     ouvertes
    -0.46
     Schenectady
    -0.46
     yaka
    -0.45
    
    -0.45
    Honolulu
    -0.45
    abestanden
    -0.44
    POSITIVE LOGITS
     London
    0.93
     British
    0.89
     Britain
    0.85
     UK
    0.82
    London
    0.82
     Londra
    0.81
    British
    0.79
    -£
    0.78
    UK
    0.78
     Britons
    0.78
    Activations Density 2.447%

    No Known Activations