© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9951
    Prev
    Next
    INDEX
    Explanations

    discussions of human rights violations and political persecution

    oai_token-act-pair · gemini-2.0-flash

    Imprisonment and oppression

    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
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.59
    addCriterion
    -0.55
    InvalidProtocol
    -0.54
     Réponses
    -0.52
    GEBURTSDATUM
    -0.49
     volgen
    -0.48
    Trou
    -0.48
     stanovnika
    -0.47
    errHandler
    -0.47
    Cyfeiriadau
    -0.46
    POSITIVE LOGITS
    astéroïdes
    0.82
     assassinated
    0.57
    abank
    0.54
    ceous
    0.52
     initWithFrame
    0.52
     murdered
    0.50
    ArrowToggle
    0.49
    idency
    0.48
    uremberg
    0.48
     berle
    0.48
    Activations Density 3.670%

    No Known Activations