Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14782
    Prev
    Next
    INDEX
    Explanations

    text about Mexican trade unions or worker organizations

    oai_token-act-pair · gemini-2.0-flash

    labor unions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ConstraintSet
    -0.47
    noks
    -0.45
     externi
    -0.44
    RectangleBorder
    -0.44
    xymatrix
    -0.42
    〗
    -0.42
    Demografía
    -0.41
    FontStyle
    -0.41
    vatar
    -0.41
    fillna
    -0.41
    POSITIVE LOGITS
     union
    2.22
     unions
    1.96
    union
    1.87
     Union
    1.73
     UNION
    1.73
     Unions
    1.70
    Union
    1.67
    UNION
    1.58
     labor
    1.55
     trade
    1.37
    Activations Density 1.119%

    No Known Activations