© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12186
    Prev
    Next
    INDEX
    Explanations

    mentions of Africa, Africans, and related geographical terms, especially in the context of historical or scientific discussions

    oai_token-act-pair · gemini-2.0-flash

    race

    np_max-act · gemini-2.0-flash

    continents

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    African

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     στιγ
    -0.57
     sitten
    -0.53
    piram
    -0.52
     déput
    -0.51
    webElementXpaths
    -0.50
    Hochspringen
    -0.50
     mín
    -0.49
     оригіналу
    -0.48
     sleeve
    -0.48
    Rüyada
    -0.47
    POSITIVE LOGITS
    industan
    0.75
     European
    0.68
    AddTagHelper
    0.67
     continent
    0.64
     Europe
    0.64
    aronder
    0.63
    Continental
    0.63
    AnchorStyles
    0.61
    ✨:
    0.61
     Continental
    0.61
    Activations Density 0.698%

    No Known Activations