© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12155
    Prev
    Next
    INDEX
    Explanations

    mentions of the mistreatment of people in Africa.

    oai_token-act-pair · gemini-2.0-flash

    South

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Composable
    -0.61
     Minden
    -0.46
     NDL
    -0.46
     Mongol
    -0.45
     Molo
    -0.45
    meln
    -0.43
    viano
    -0.43
    sik
    -0.42
     Brits
    -0.42
     Mersey
    -0.41
    POSITIVE LOGITS
     South
    1.94
    South
    1.83
     SOUTH
    1.53
    SOUTH
    1.37
    south
    1.23
     Zuid
    1.23
     south
    1.18
     SA
    1.17
     Sud
    1.06
    南
    1.02
    Activations Density 1.909%

    No Known Activations