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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1718
    Prev
    Next
    INDEX
    Explanations

    words related to splitting things into multiple sections or categories

    oai_token-act-pair · gemini-2.0-flash

    sections, parts, or steps

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     part
    -2.38
    part
    -2.05
    Part
    -1.82
     Part
    -1.68
     parte
    -1.58
     PART
    -1.44
     часть
    -1.39
     частью
    -1.30
     Teil
    -1.30
    PART
    -1.27
    POSITIVE LOGITS
    клопе
    0.60
    StoryboardSegue
    0.59
    gameserver
    0.57
    fels
    0.56
    rinfo
    0.54
    LayoutStyle
    0.54
    +#+#
    0.52
    imų
    0.51
    #![
    0.50
     való
    0.49
    Activations Density 4.894%

    No Known Activations