© 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. 14606
    Prev
    Next
    INDEX
    Explanations

    text related to political unrest and violence, especially in Muslim countries

    oai_token-act-pair · gemini-2.0-flash

    violence and unrest

    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
     disambiguazione
    -0.88
     betweenstory
    -0.78
    oredCriteria
    -0.75
    Tembelea
    -0.66
    :✨
    -0.65
    LookAnd
    -0.64
    rungsseite
    -0.62
    ंदीखरीदारी
    -0.62
    Rüyada
    -0.62
    TagMode
    -0.61
    POSITIVE LOGITS
     correctes
    0.54
     Less
    0.52
    wendungs
    0.50
    ornal
    0.47
    商品説明
    0.47
     controlado
    0.47
    Less
    0.47
    cire
    0.46
    acker
    0.46
    culate
    0.46
    Activations Density 16.109%

    No Known Activations