© 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. 7235
    Prev
    Next
    INDEX
    Explanations

    instances of descriptions pertaining to political science, treaties, and international relations

    oai_token-act-pair · gemini-2.0-flash

    model, template

    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
    Negative Logits
    CppCodeGen
    -0.62
     associés
    -0.59
     especiais
    -0.59
     spéciaux
    -0.58
     tantum
    -0.56
     esprits
    -0.55
     gomma
    -0.55
     especiales
    -0.54
     gând
    -0.54
     abbond
    -0.53
    POSITIVE LOGITS
     model
    0.79
     roadmap
    0.73
     template
    0.71
     manual
    0.68
     proto
    0.67
     archetype
    0.66
    webElementXpaths
    0.63
     guide
    0.63
     models
    0.61
     road
    0.61
    Activations Density 2.265%

    No Known Activations