© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13422
    Prev
    Next
    INDEX
    Explanations

    mentions of airports and related words like flight and arrival, especially when they're near city names.

    oai_token-act-pair · gemini-2.0-flash

    airports and air travel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    webElement
    -0.42
    openqa
    -0.39
     DON
    -0.36
    Doh
    -0.36
    loit
    -0.36
     DRC
    -0.36
    Don
    -0.36
    findViewById
    -0.35
    Vaya
    -0.35
    vw
    -0.35
    POSITIVE LOGITS
     Landing
    0.79
     landing
    0.77
     Aircraft
    0.77
     démocratie
    0.76
     landings
    0.76
    GEBURTSDATUM
    0.75
    Landing
    0.75
     Efq
    0.74
     Monfieur
    0.74
     חיצוניים
    0.73
    Activations Density 1.949%

    No Known Activations