© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    articles or news items about Chinese government corruption

    oai_token-act-pair · gemini-2.0-flash

    China

    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
     Chinese
    -2.27
    Chinese
    -2.02
     China
    -2.00
     chinese
    -1.99
     CHINESE
    -1.90
    China
    -1.81
     CHINA
    -1.76
     chines
    -1.74
     китай
    -1.73
     Chines
    -1.70
    POSITIVE LOGITS
    odori
    0.50
     الحره
    0.49
    FTFY
    0.48
    enumi
    0.44
     reb
    0.42
    eeq
    0.42
     cốc
    0.41
     Đường
    0.40
    sunter
    0.40
    ياة
    0.39
    Activations Density 0.935%

    No Known Activations