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. 1696
    Prev
    Next
    INDEX
    Explanations

    phone numbers and URLs.

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis

    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
     congruence
    -0.49
     phones
    -0.48
     tensions
    -0.42
     telephones
    -0.41
     mobiles
    -0.40
     five
    -0.37
     telefonu
    -0.36
     transitions
    -0.36
     developments
    -0.36
     proliferation
    -0.36
    POSITIVE LOGITS
    ⓧ
    0.92
    Geplaatst
    0.81
    Externé
    0.78
     nahilalakip
    0.77
     chi̍t
    0.77
     onOptions
    0.76
    Portail
    0.76
    IsContent
    0.75
     intptr
    0.75
    +:+
    0.73
    Activations Density 12.847%

    No Known Activations