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. 1626
    Prev
    Next
    INDEX
    Explanations

    Spanish text relating to chess, Panamanian publishers, or related organizations

    oai_token-act-pair · gemini-2.0-flash

    Spanish language related

    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
     hObject
    -0.63
     }}"></
    -0.60
    guenos
    -0.57
     StatelessWidget
    -0.55
    ضايا
    -0.54
     חיצוניים
    -0.53
    Tikang
    -0.52
    fourths
    -0.52
    krát
    -0.52
     Himo
    -0.51
    POSITIVE LOGITS
    minecraft
    0.62
    openConnection
    0.62
    ंदीखरीदारी
    0.60
     Illuminate
    0.59
    apimachinery
    0.53
    WithMany
    0.52
    χε
    0.51
    ัพท์
    0.49
     FishBase
    0.48
    osomes
    0.47
    Activations Density 0.267%

    No Known Activations