© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8391
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to international relations, specifically those involving Iran, Russia, Nuclear Weapons and the United States.

    oai_token-act-pair · gemini-2.0-flash

    Iran nuclear agreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     expected
    -1.66
     Expected
    -1.47
    expected
    -1.47
     EXPECT
    -1.42
     expect
    -1.42
     expects
    -1.33
    Expected
    -1.30
     expectation
    -1.25
    expect
    -1.21
     expecting
    -1.20
    POSITIVE LOGITS
    IsContent
    0.49
    asiswa
    0.48
     Agreement
    0.46
     дописавши
    0.44
    Agreement
    0.43
     aikaa
    0.43
     الإنترنت
    0.42
    ganos
    0.42
    gebra
    0.42
     Rennen
    0.42
    Activations Density 0.416%

    No Known Activations