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. 1609
    Prev
    Next
    INDEX
    Explanations

    seemingly random tokens in technical documentation

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     next
    -2.19
    next
    -1.94
    Next
    -1.58
     Next
    -1.55
     NEXT
    -1.50
    NEXT
    -1.42
     nästa
    -1.16
     prochain
    -1.13
    下一
    -1.10
     last
    -1.09
    POSITIVE LOGITS
    ########.
    0.75
    httphttps
    0.68
    tvguidetime
    0.68
    脚注の使い方
    0.64
     }{@
    0.64
    encodeWith
    0.63
    SpringBootTest
    0.60
    XmlAccessType
    0.60
    WriteBarrier
    0.59
    nloa
    0.58
    Activations Density 9.325%

    No Known Activations