© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7367
    Prev
    Next
    INDEX
    Explanations

    words in a political or governmental context

    oai_token-act-pair · gemini-2.0-flash

    Politics and world news

    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
    Negative Logits
     getItemId
    -0.54
    yntaxException
    -0.52
    tu
    -0.49
     EconPapers
    -0.45
    setPointSize
    -0.44
     MaterialApp
    -0.44
    锈钢
    -0.44
    HR
    -0.44
    Tess
    -0.43
     tải
    -0.43
    POSITIVE LOGITS
    asanjo
    0.67
     Савезне
    0.63
    
    0.63
     Obrador
    0.63
    sikker
    0.61
     centre
    0.60
    leſs
    0.59
     governors
    0.59
     centro
    0.59
    ậm
    0.59
    Activations Density 1.175%

    No Known Activations