© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2208
    Prev
    Next
    INDEX
    Explanations

    text related to social issues such as race, discrimination, and slavery.

    oai_token-act-pair · gemini-2.0-flash

    ethnicities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AddTagHelper
    -0.80
    Rujuakan
    -0.65
    tanleria
    -0.65
     Púb
    -0.61
    ⓘ
    -0.56
    FunctionFlags
    -0.54
     materna
    -0.54
     octaves
    -0.54
     PyTuple
    -0.54
     canina
    -0.54
    POSITIVE LOGITS
     Asians
    0.84
     African
    0.73
     Africans
    0.73
     Asian
    0.71
     Hispanic
    0.71
    Asian
    0.68
     blacks
    0.65
     Indians
    0.64
     Hispanics
    0.64
     Latinos
    0.64
    Activations Density 2.314%

    No Known Activations