© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4872
    Prev
    Next
    INDEX
    Explanations

    words that appear near commas, especially when describing the persecution of minority groups during World War II

    oai_token-act-pair · gemini-2.0-flash

    Discrimination and violence

    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
    initComponents
    -0.66
    complexContent
    -0.63
    withIdentifier
    -0.60
     venons
    -0.58
    ंदीखरीदारी
    -0.56
    льше
    -0.55
     magasiner
    -0.54
    Thin
    -0.53
    DotNetBar
    -0.52
    höhung
    -0.51
    POSITIVE LOGITS
    '],'
    0.58
    xase
    0.56
    UnknownFields
    0.51
    HasBeenSet
    0.50
    engertian
    0.48
    BIDDEN
    0.48
     Frist
    0.47
    uggest
    0.47
     Sun
    0.47
    ETCH
    0.47
    Activations Density 1.973%

    No Known Activations