© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10901
    Prev
    Next
    INDEX
    Explanations

    references to countries, enslavement, jurisprudence, and workforce

    oai_token-act-pair · gemini-2.0-flash

    country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    sizeCache
    -0.85
    InjectAttribute
    -0.80
    THAT
    -0.79
     that
    -0.76
    <bos>
    -0.75
    uxxxx
    -0.73
    SourceChecksum
    -0.73
     particulières
    -0.68
     That
    -0.68
    that
    -0.66
    POSITIVE LOGITS
     ChromeDriver
    0.54
    غم
    0.54
    存于互联网档案馆
    0.46
     Iter
    0.45
     CONGRESS
    0.44
     nao
    0.43
    URLException
    0.43
     UITableView
    0.43
     birch
    0.42
     Pingback
    0.42
    Activations Density 1.524%

    No Known Activations