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. 2335
    Prev
    Next
    INDEX
    Explanations

    concepts of physics and mathematics

    oai_token-act-pair · gemini-2.0-flash

    quantum physics

    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
     physics
    -0.91
     física
    -0.87
    physics
    -0.83
     Physics
    -0.82
     physical
    -0.81
     fisica
    -0.78
    phys
    -0.78
    physical
    -0.74
    Physical
    -0.73
    Physics
    -0.73
    POSITIVE LOGITS
    AddAttribute
    0.61
    Datuak
    0.58
    Diwedd
    0.58
    AutoScale
    0.57
    MemoryWarning
    0.57
    principalTable
    0.56
    HomeAsUpEnabled
    0.55
    Followed
    0.53
    ollection
    0.52
     Occasional
    0.52
    Activations Density 10.242%

    No Known Activations