© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9026
    Prev
    Next
    INDEX
    Explanations

    references to race, ethnicity, and demographic representation

    oai_token-act-pair · gemini-2.0-flash

    race and ethnicity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     bpy
    -0.78
    DebuggerStep
    -0.60
    phosa
    -0.60
    GroupLayout
    -0.57
    providedIn
    -0.56
    WriteTagHelper
    -0.56
    OCCURRED
    -0.53
    })));
    -0.52
     <>",
    -0.52
    parsedMessage
    -0.52
    POSITIVE LOGITS
    expandindo
    0.58
     AssemblyCulture
    0.57
     Estar
    0.50
    Controllo
    0.50
    تقاوى
    0.48
    Autoritní
    0.47
     استنادى
    0.45
    LEncoder
    0.45
     enceinte
    0.44
     Dominant
    0.43
    Activations Density 12.111%

    No Known Activations