© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15373
    Prev
    Next
    INDEX
    Explanations

    words related to Korean media, especially Korean names and titles

    oai_token-act-pair · gemini-2.0-flash

    "South" location

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Korean
    -0.68
    Korean
    -0.65
    TabStop
    -0.65
     Korea
    -0.58
     korean
    -0.54
     Baird
    -0.53
     Horizons
    -0.52
     समीक्षक
    -0.52
    metria
    -0.51
     Corsica
    -0.51
    POSITIVE LOGITS
     South
    1.33
    South
    1.23
     SOUTH
    0.95
    south
    0.76
    SOUTH
    0.75
     south
    0.68
    南
    0.58
     Johannesburg
    0.56
     南
    0.56
    IUrlHelper
    0.52
    Activations Density 7.254%

    No Known Activations