© 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. 2722
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to political and social structures, especially those involving conflict and governance.

    oai_token-act-pair · gemini-2.0-flash

    historical and political systems

    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
     cipolla
    -0.66
     timeval
    -0.49
    tad
    -0.48
     ModelExpression
    -0.48
    BoxShadow
    -0.47
     esper
    -0.45
     CreateTagHelper
    -0.45
    |}{
    -0.44
     vicenda
    -0.43
    RegressionTest
    -0.43
    POSITIVE LOGITS
     shogun
    0.70
     iNdEx
    0.65
    IndentedString
    0.64
     superstition
    0.61
     tariffs
    0.60
     taxes
    0.60
     nobility
    0.59
     taxation
    0.59
     Manifest
    0.58
    CppMethod
    0.58
    Activations Density 5.563%

    No Known Activations