© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10532
    Prev
    Next
    INDEX
    Explanations

    mentions of the United States and of other countries, governments, and international relations, especially in the context of trade and assistance.

    oai_token-act-pair · gemini-2.0-flash

    arms sales

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     onStop
    -0.41
    ational
    -0.41
    tical
    -0.39
    itis
    -0.37
     Erzb
    -0.36
    calypse
    -0.35
     libur
    -0.35
     Editors
    -0.35
     Chair
    -0.35
     gez
    -0.35
    POSITIVE LOGITS
     دیکھیے
    0.77
    таратура
    0.75
     незавершена
    0.75
    хьтан
    0.74
    ^(@)
    0.71
     pinulongan
    0.70
    Билгалдахарш
    0.69
    脚注の使い方
    0.68
    adpleegd
    0.67
     Chwiliwch
    0.66
    Activations Density 0.485%

    No Known Activations