© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8721
    Prev
    Next
    INDEX
    Explanations

    references to Japan and Asian countries

    oai_token-act-pair · gemini-2.0-flash

    Japan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Japan
    -1.84
     Japanese
    -1.70
    Japan
    -1.62
     japan
    -1.58
     JAPAN
    -1.52
    Japanese
    -1.46
     Japón
    -1.45
     Giappone
    -1.36
     япон
    -1.36
     japanese
    -1.34
    POSITIVE LOGITS
     مرئيه
    0.57
    verwijspagina
    0.54
     dolo
    0.51
    Gön
    0.51
    SizeF
    0.50
    INCLUDED
    0.49
     Exactos
    0.47
     saus
    0.47
    bukkit
    0.47
    Források
    0.47
    Activations Density 1.163%

    No Known Activations