© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15114
    Prev
    Next
    INDEX
    Explanations

    mentions of labor unions and related political endorsements

    oai_token-act-pair · gemini-2.0-flash

    Unions and labor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    HasForeignKey
    -0.60
    PreExecute
    -0.59
    MemoryWarning
    -0.59
     Pingback
    -0.56
     Dostupné
    -0.56
    клопе
    -0.55
    blende
    -0.55
    出版年
    -0.54
     ComVisible
    -0.54
     GenerationType
    -0.54
    POSITIVE LOGITS
     Conservatives
    0.51
     Conservative
    0.51
    Conservative
    0.49
     Coalition
    0.47
     Consultants
    0.46
     Consultancy
    0.45
     appointed
    0.45
    umbang
    0.44
     Subsid
    0.44
    kiwa
    0.44
    Activations Density 8.882%

    No Known Activations