© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6693
    Prev
    Next
    INDEX
    Explanations

    political or legislative updates and voting

    oai_token-act-pair · gemini-2.0-flash

    Politics and legislation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RegressionTest
    -0.55
    WebVitals
    -0.50
    tagext
    -0.50
    WriteBarrier
    -0.49
     washes
    -0.47
    SaveChangesAsync
    -0.45
    ู่
    -0.44
     curé
    -0.42
    ValueStyle
    -0.41
    RunAsync
    -0.41
    POSITIVE LOGITS
     pinulongan
    0.85
     nakalista
    0.68
    AndEndTag
    0.65
    PyExc
    0.64
     spending
    0.63
     Waray
    0.57
    dymyr
    0.56
    CreateMap
    0.56
     Spending
    0.55
     ویکی‌پدی
    0.55
    Activations Density 1.059%

    No Known Activations