© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12492
    Prev
    Next
    INDEX
    Explanations

    mentions of the Patriot Act in the context of 9/11

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     GenerationType
    -0.71
    ConstraintMaker
    -0.69
    ChildScrollView
    -0.69
    SequentialGroup
    -0.64
     amet
    -0.61
    tahui
    -0.60
    IsContent
    -0.59
     kaynağından
    -0.59
    SOUNDBITE
    -0.59
    TestingModule
    -0.58
    POSITIVE LOGITS
    ők
    0.41
    toh
    0.41
     sienten
    0.41
    šanai
    0.40
     rette
    0.39
     Wiktionnaire
    0.39
    lixir
    0.38
     enfrentan
    0.38
     SAVE
    0.38
    zeczy
    0.37
    Activations Density 0.598%

    No Known Activations