© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15994
    Prev
    Next
    INDEX
    Explanations

    text discussing race and ethnic groups, especially regarding disparities, representation, and historical context like slavery.

    oai_token-act-pair · gemini-2.0-flash

    race and ethnicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    AnimationsModule
    -0.61
    LogFactory
    -0.57
    complexType
    -0.54
    rafas
    -0.52
    fasst
    -0.51
     Beers
    -0.51
     actuator
    -0.50
     lesbians
    -0.50
     seno
    -0.49
    ParallelGroup
    -0.49
    POSITIVE LOGITS
    ########.
    0.62
    RegressionTest
    0.60
     متعلقه
    0.54
    berdayakan
    0.54
    Спољашње
    0.54
    }'.
    0.51
     Paglinawan
    0.50
     gainera
    0.50
     Retrieved
    0.49
    Groeten
    0.49
    Activations Density 34.309%

    No Known Activations