© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11557
    Prev
    Next
    INDEX
    Explanations

    mentions of politicians, countries, military, and espionage agencies and activities

    oai_token-act-pair · gemini-2.0-flash

    Geopolitics involving Ukraine, Russia, Taiwan

    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
     itſelf
    -0.74
     leſs
    -0.65
    ſelves
    -0.65
     ſmall
    -0.64
    RegressionTest
    -0.63
     ―――――
    -0.62
     houſe
    -0.62
    ſelf
    -0.62
     Diſ
    -0.61
     XO
    -0.61
    POSITIVE LOGITS
    newArrayList
    0.56
    Personendaten
    0.55
    PropertyChanging
    0.54
    aspectj
    0.50
    rawDesc
    0.49
    afficheront
    0.48
    richTextPanel
    0.46
    LEVANT
    0.45
    setLayoutManager
    0.45
     kív
    0.44
    Activations Density 1.207%

    No Known Activations