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. 1543
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to figures, tables, and equations

    oai_token-act-pair · gemini-2.0-flash

    code or math snippets

    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
     myſelf
    -1.01
     Efq
    -0.90
     themſelves
    -0.86
     purpoſe
    -0.84
     Reſ
    -0.82
     Jefus
    -0.80
     himſelf
    -0.79
     pleaſure
    -0.79
     faſt
    -0.78
     Eſ
    -0.77
    POSITIVE LOGITS
    }{-
    0.69
    ="@+
    0.66
     '{@
    0.66
    hasMoreElements
    0.60
    ">//
    0.59
    }{
    0.59
    |}\
    0.59
    complexType
    0.58
    }{$
    0.58
    ReusableCell
    0.56
    Activations Density 3.829%

    No Known Activations