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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14150
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Arrows/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     itſelf
    -1.64
     myſelf
    -1.52
     themſelves
    -1.37
     Majefty
    -1.34
     himſelf
    -1.30
     Monfieur
    -1.30
     doubtnut
    -1.30
    ſelves
    -1.29
     purpoſe
    -1.28
     Reſ
    -1.27
    POSITIVE LOGITS
     
    0.69
     Z
    0.64
     S
    0.62
     De
    0.60
     T
    0.57
     "
    0.57
     C
    0.57
     de
    0.55
     A
    0.55
     z
    0.55
    Activations Density 4.469%

    No Known Activations