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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11123
    Prev
    Next
    INDEX
    Explanations

    scientific names of species with emphasis on the endings

    oai_token-act-pair · gemini-2.0-flash

    words related to medical conditions and biological terms

    np_token-act-pair-logits · gpt-4o-mini

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.94
    boyfriend
    -0.83
     husband
    -0.81
    husband
    -0.75
     boyfriend
    -0.72
     Husband
    -0.68
    owanym
    -0.65
    Husband
    -0.60
     boyfriends
    -0.60
     chồng
    -0.59
    POSITIVE LOGITS
     wife
    0.75
    ńskiej
    0.70
     istrinya
    0.65
     какую
    0.64
     тази
    0.63
     quella
    0.63
     taką
    0.63
     takiej
    0.61
     seine
    0.61
    Одна
    0.60
    Activations Density 0.410%

    No Known Activations