© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6793
    Prev
    Next
    INDEX
    Explanations

    words or phrases relating to government, rules, and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    government departments or sectors

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

    government ministries

    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
    urlpatterns
    -0.57
    ThroughAttribute
    -0.53
    OrBuilder
    -0.53
    ChildScrollView
    -0.47
    awtextra
    -0.45
     Familienname
    -0.44
    Xiv
    -0.44
    ArgumentParser
    -0.44
    収録曲
    -0.42
    ็จ
    -0.42
    POSITIVE LOGITS
     Health
    1.08
     Transport
    0.91
    Health
    0.90
     Education
    0.90
     Finance
    0.88
     Interior
    0.88
     Environment
    0.87
     Agriculture
    0.84
     Transportation
    0.83
    Environment
    0.81
    Activations Density 2.250%

    No Known Activations