Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2329
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup and math symbols.

    oai_token-act-pair · gemini-2.0-flash

    Latex syntax

    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
     purpoſe
    -0.69
     Salmo
    -0.68
     themſelves
    -0.65
     appellants
    -0.65
     adipose
    -0.64
     skulls
    -0.63
     trombone
    -0.63
     Clovis
    -0.62
     Polity
    -0.62
     barbarians
    -0.62
    POSITIVE LOGITS
    AccessFile
    0.66
     F
    0.56
    URLException
    0.55
    +#+
    0.54
    protoc
    0.54
    EndContext
    0.54
     Italijani
    0.54
    CodeAttribute
    0.53
    Tazama
    0.52
    InputBorder
    0.50
    Activations Density 8.491%

    No Known Activations