© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8946
    Prev
    Next
    INDEX
    Explanations

    mentions of Papua New Guinea and the Pacific Islands, especially in the context of studies

    oai_token-act-pair · gemini-2.0-flash

    Pacific islanders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -1.00
    MLLoader
    -0.99
    ViewFeatures
    -0.96
    AddHtmlAttribute
    -0.95
    WebElementEntity
    -0.91
    adaptiveStyles
    -0.91
    rungsseite
    -0.91
    UserScript
    -0.89
    tvguidetime
    -0.88
    :✨
    -0.87
    POSITIVE LOGITS
     National
    0.50
    oflavin
    0.47
    skab
    0.44
     propuesta
    0.43
    National
    0.43
     desorden
    0.43
    vanje
    0.42
     Kel
    0.41
     Национа
    0.40
     tratados
    0.40
    Activations Density 1.066%

    No Known Activations