© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    words related to nightlife, bars, and having a good time

    oai_token-act-pair · gemini-2.0-flash

    nightlife

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    abestanden
    -0.80
    Hentet
    -0.78
    WebElementEntity
    -0.77
     فريبيس
    -0.73
    InjectAttribute
    -0.70
    SPATH
    -0.69
    matchCondition
    -0.67
     متعلقه
    -0.67
    ValueGeneration
    -0.67
     BorderSide
    -0.65
    POSITIVE LOGITS
     bar
    0.76
     cocktails
    0.73
     drink
    0.72
    bar
    0.69
     cocktail
    0.68
     drinks
    0.67
    Bar
    0.67
     Cocktail
    0.65
    cocktail
    0.63
     Bar
    0.63
    Activations Density 0.596%

    No Known Activations