© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10341
    Prev
    Next
    INDEX
    Explanations

    discussion of violence and unrest in a historical context

    oai_token-act-pair · gemini-2.0-flash

    gas-related terms

    np_token-act-pair-logits · gpt-4o-mini

    tear gas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Normdatei
    -0.48
    SequentialGroup
    -0.47
    DeleteCommand
    -0.47
     trasc
    -0.46
     IConfiguration
    -0.45
    lapsingToolbar
    -0.45
    GeneratedCode
    -0.45
    CommonModule
    -0.44
     Sponsored
    -0.44
    XmlType
    -0.44
    POSITIVE LOGITS
     gas
    1.13
    gas
    0.98
     tear
    0.97
    Gas
    0.90
     Gas
    0.85
    tear
    0.84
     Tear
    0.78
    GAS
    0.75
     gases
    0.74
    Tear
    0.73
    Activations Density 1.360%

    No Known Activations