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. 5879
    Prev
    Next
    INDEX
    Explanations

    code snippets/segments, especially in languages like Java, PHP, and Javascript

    oai_token-act-pair · gemini-2.0-flash

    Spanish language tokens

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

    Spanish/Portuguese stop words

    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
     ainfi
    -1.50
     Efq
    -1.43
     Theſe
    -1.40
     avoient
    -1.38
     normaux
    -1.38
     itſelf
    -1.38
     CHAPITRE
    -1.38
     Monfieur
    -1.37
     financières
    -1.36
     étoient
    -1.33
    POSITIVE LOGITS
     de
    0.82
     des
    0.71
     la
    0.58
     que
    0.56
     c
    0.54
     en
    0.52
     un
    0.52
     est
    0.47
     a
    0.47
     le
    0.47
    Activations Density 7.538%

    No Known Activations