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. 5858
    Prev
    Next
    INDEX
    Explanations

    HTML paragraph tags

    oai_token-act-pair · gemini-2.0-flash

    paragraph endings and transitions

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

    p

    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
     تضيفلها
    -1.16
    RenderAtEndOf
    -1.13
     незавершена
    -1.11
     myſelf
    -1.09
    StoryboardSegue
    -1.07
     MainAxisSize
    -1.03
    tagHelperRunner
    -1.03
     itſelf
    -1.02
     المعيارى
    -1.02
    awtextra
    -0.99
    POSITIVE LOGITS
     as
    0.51
    <
    0.43
    -
    0.41
    as
    0.41
     of
    0.40
    ...
    0.39
    <eos>
    0.38
    B
    0.38
    A
    0.37
    中で
    0.36
    Activations Density 0.102%

    No Known Activations