© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9413
    Prev
    Next
    INDEX
    Explanations

    language related to economics and politics, especially in relation to China.

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Kaieteur
    -0.60
    Hozzáférés
    -0.52
    tella
    -0.47
     thế
    -0.41
     Вікіпе
    -0.41
     vers
    -0.41
    BeginContext
    -0.40
    FromArgb
    -0.40
    Michel
    -0.38
     talaga
    -0.38
    POSITIVE LOGITS
     China
    1.35
     Chinese
    1.26
     CHINA
    1.25
     CHINESE
    1.25
    China
    1.22
    Chinese
    1.16
     chinoise
    1.15
     chinois
    1.14
     chinese
    1.13
     china
    1.12
    Activations Density 1.253%

    No Known Activations