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. 1755
    Prev
    Next
    INDEX
    Explanations

    legal citations and references

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     etc
    -0.47
     per
    -0.44
     for
    -0.43
     For
    -0.42
     **
    -0.42
     s
    -0.42
     the
    -0.42
     ()
    
    -0.40
    ++
    
    -0.39
     Set
    -0.39
    POSITIVE LOGITS
    Geplaatst
    0.73
    ########.
    0.65
     BoxDecoration
    0.62
    
    0.57
    出版年
    0.54
    Jaime
    0.51
    Rhestr
    0.51
    
    0.50
    Adriana
    0.50
    XmlAccessorType
    0.49
    Activations Density 9.563%

    No Known Activations