© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11026
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to politics, government, and the state.

    oai_token-act-pair · gemini-2.0-flash

    political

    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
    AccessorTable
    -0.91
    ArgsConstructor
    -0.86
    UnsafeEnabled
    -0.81
    ViewImports
    -0.73
    ValueStyle
    -0.65
     NSCoder
    -0.60
     дописавши
    -0.58
    DoubleQuotes
    -0.57
    AndEndTag
    -0.56
    EndContext
    -0.53
    POSITIVE LOGITS
    sidemargin
    0.52
     recev
    0.50
     >=",
    0.48
    tagez
    0.48
     Farmhouse
    0.47
     Fug
    0.46
     Muske
    0.45
    Fug
    0.45
    améli
    0.45
    Funcion
    0.44
    Activations Density 1.695%

    No Known Activations