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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16291
    Prev
    Next
    INDEX
    Explanations

    sentences discussing restrictions placed on something

    oai_token-act-pair · gemini-2.0-flash

    limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    WebElementEntity
    -0.62
    évaluateur
    -0.59
    piram
    -0.51
    keyColumn
    -0.48
     vues
    -0.47
    Spoljašnje
    -0.47
    ंदीखरीदारी
    -0.45
    icrous
    -0.44
    atguigu
    -0.44
    xically
    -0.44
    POSITIVE LOGITS
     canst
    0.59
     Anfitrión
    0.56
    المناصب
    0.56
    zköz
    0.55
     تانيه
    0.53
     UITableViewCell
    0.52
    ડી
    0.52
     Económica
    0.52
     allowed
    0.52
     twij
    0.52
    Activations Density 0.785%

    No Known Activations