© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12854
    Prev
    Next
    INDEX
    Explanations

    content related to democracy, elections, social movements, and discussions of political systems, especially in the context of Latin America

    oai_token-act-pair · gemini-2.0-flash

    political economic social discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     مرئيه
    -0.57
     ControllerBase
    -0.55
    Попис
    -0.55
     CommandType
    -0.54
    setLayoutManager
    -0.53
     iload
    -0.52
    intios
    -0.50
     ucha
    -0.50
     TabLayout
    -0.49
     Sosial
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.56
     states
    0.51
     willed
    0.50
    cloudfront
    0.49
    seitige
    0.49
     blows
    0.47
    LIO
    0.47
    ungsbedingungen
    0.47
     presente
    0.47
    ніципалі
    0.47
    Activations Density 13.574%

    No Known Activations