© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15606
    Prev
    Next
    INDEX
    Explanations

    text related to deaths, middle-eastern people, and/or middle-european places

    oai_token-act-pair · gemini-2.0-flash

    Mortality/terrorism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    GraphicsUnit
    -0.70
     تضيفلها
    -0.69
    存于互联网档案馆
    -0.66
    ValueStyle
    -0.66
    Datuak
    -0.64
     noqa
    -0.62
    RuleContext
    -0.60
    BagLayout
    -0.59
    pushFollow
    -0.59
    localctx
    -0.59
    POSITIVE LOGITS
     NSCoder
    0.71
     specifically
    0.45
     infine
    0.44
    corer
    0.42
    יד
    0.41
     SqlCommand
    0.41
    Française
    0.38
    となると
    0.38
     algorithm
    0.37
    なか
    0.37
    Activations Density 0.686%

    No Known Activations