© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1693
    Prev
    Next
    INDEX
    Explanations

    mentions of international politics and politicians, especially related to NATO, the US and Russia

    oai_token-act-pair · gemini-2.0-flash

    NATO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    gan
    -0.49
     kort
    -0.42
     K
    -0.41
    product
    -0.40
    сми
    -0.40
     terme
    -0.40
     gene
    -0.39
    poo
    -0.39
     règlement
    -0.39
    <strong>
    -0.38
    POSITIVE LOGITS
    PerformLayout
    0.96
    abestanden
    0.95
    findpost
    0.93
    WindowConstants
    0.93
     Efq
    0.92
    ſelves
    0.90
    ContentAsync
    0.87
     nakalista
    0.86
     initComponents
    0.85
     InputDecoration
    0.84
    Activations Density 1.797%

    No Known Activations