© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14593
    Prev
    Next
    INDEX
    Explanations

    mentions of Korean culture, especially food and TV dramas

    oai_token-act-pair · gemini-2.0-flash

    Korean language/culture

    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
     South
    -2.11
    South
    -1.97
     SOUTH
    -1.71
    SOUTH
    -1.64
     south
    -1.50
    south
    -1.48
     Korean
    -1.33
     Süd
    -1.20
     Zuid
    -1.18
     Korea
    -1.15
    POSITIVE LOGITS
     estekak
    0.66
    '}>
    0.65
     BoxFit
    0.59
    AndEndTag
    0.59
     Overton
    0.58
     Winslow
    0.57
    ActionCreators
    0.57
    öße
    0.57
    جغرافيا
    0.56
    '},
    0.55
    Activations Density 2.313%

    No Known Activations