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. 1707
    Prev
    Next
    INDEX
    Explanations

    math, equations, and associated symbols

    oai_token-act-pair · gemini-2.0-flash

    math expressions

    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
    ?
    -1.42
    !
    -1.40
    ;
    -1.14
    :
    -0.91
    >
    -0.90
    ))
    -0.88
    ();
    -0.80
    ++;
    -0.78
    *
    -0.77
    ,”
    -0.75
    POSITIVE LOGITS
     utafitiHapana
    0.85
    abestanden
    0.73
    GEBURTSDATUM
    0.72
     سكانية
    0.72
    )*/
    0.71
     المعيارى
    0.66
     otomatig
    0.65
     podjela
    0.65
    ########.
    0.64
    oa̍t
    0.64
    Activations Density 32.183%

    No Known Activations