© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14534
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly found in political documents and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Political/legal events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     AssemblyTitle
    -0.75
    OGND
    -0.73
    SourceChecksum
    -0.68
    GeneratedCode
    -0.64
    igshid
    -0.62
     GenerationType
    -0.62
     "..\..\..\
    -0.60
    曖昧さ回避
    -0.60
    WaitGroup
    -0.60
     Wikimedijinoj
    -0.60
    POSITIVE LOGITS
    TAWA
    0.47
     drunkenness
    0.47
    ableness
    0.46
    }-${
    0.46
    pyx
    0.45
     senare
    0.44
     happiest
    0.44
     daily
    0.44
     calitate
    0.43
    %/
    0.42
    Activations Density 2.071%

    No Known Activations