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. 6013
    Prev
    Next
    INDEX
    Explanations

    technical writing in medical publications

    oai_token-act-pair · gemini-2.0-flash

    biomedical terminology or references

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

    scientific experiments

    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
    bkz
    -0.59
    
    -0.53
    ⓧ
    -0.50
     noqa
    -0.49
    ruptedException
    -0.49
    istoitu
    -0.46
    AutoresizingMask
    -0.46
     continúas
    -0.45
     transfieras
    -0.45
    ագրություններ
    -0.45
    POSITIVE LOGITS
    انيف
    0.59
    ENAME
    0.54
    treated
    0.54
     group
    0.53
     animal
    0.51
     model
    0.51
     /\.
    0.49
     gynnwys
    0.49
    ciss
    0.47
     modelo
    0.47
    Activations Density 6.666%

    No Known Activations