© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6991
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, locations, and events, especially related to international relations and potential conflicts.

    oai_token-act-pair · gemini-2.0-flash

    North Korea

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    emlrt
    -0.56
     uintptr
    -0.47
    Décès
    -0.45
    AFFIRMED
    -0.44
     Falle
    -0.43
    ربای
    -0.43
    rety
    -0.42
     incorporado
    -0.42
    IFFS
    -0.42
    paths
    -0.41
    POSITIVE LOGITS
     Py
    0.78
    Py
    0.77
     North
    0.68
     py
    0.66
    North
    0.65
    Gambas
    0.58
     Cone
    0.57
    DockStyle
    0.56
    ValueStyle
    0.56
    creenshot
    0.55
    Activations Density 0.842%

    No Known Activations