© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6661
    Prev
    Next
    INDEX
    Explanations

    words related to humans being organized into groups, whether it be ethnic groups, political organizations, medical patients, etc

    oai_token-act-pair · gemini-2.0-flash

    people

    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
     ProtoMessage
    -0.84
    INSEE
    -0.83
     Theſe
    -0.81
    IVEREF
    -0.79
    Välislingid
    -0.76
     lenker
    -0.75
     HasFactory
    -0.75
     utafitiHapana
    -0.73
     pinulongan
    -0.73
     שוליים
    -0.72
    POSITIVE LOGITS
    <eos>
    0.64
     that
    0.54
     feared
    0.50
     you
    0.47
     "
    0.46
     becoming
    0.45
    名は
    0.45
     werden
    0.44
    望
    0.44
    ↵↵
    0.43
    Activations Density 3.850%

    No Known Activations