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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1039
    Prev
    Next
    INDEX
    Explanations

    gossip about celebrities, the rich and famous, and/or royalty and their lifestyle.

    oai_token-act-pair · gemini-2.0-flash

    Nonsense

    np_token-act-pair-logits · gemini-2.0-flash

    wealth and luxury

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     luxury
    -0.90
     luxurious
    -0.85
    luxury
    -0.77
     Luxury
    -0.77
     luxe
    -0.77
     Expensive
    -0.75
     Lux
    -0.73
    luxe
    -0.73
    脚注の使い方
    -0.72
     lux
    -0.71
    POSITIVE LOGITS
     prévention
    0.56
     universale
    0.54
    Javadoc
    0.51
    odorant
    0.51
     GenerationType
    0.48
    тельству
    0.48
    zaamheid
    0.48
     nhat
    0.47
    toolbox
    0.47
    ensdag
    0.47
    Activations Density 2.906%

    No Known Activations