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. 1646
    Prev
    Next
    INDEX
    Explanations

    text related to patents, inventions, material science, scientific processes, and electronic devices

    oai_token-act-pair · gemini-2.0-flash

    Energy transfer/loss

    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
     NSCoder
    -0.50
     Wikispecies
    -0.48
     bébé
    -0.47
     adulto
    -0.47
     celebrity
    -0.47
     ADULT
    -0.46
     prostitu
    -0.46
    ardonnay
    -0.46
     defaultstate
    -0.45
    útbol
    -0.45
    POSITIVE LOGITS
     dissipation
    0.62
     damping
    0.56
     heat
    0.54
     vibration
    0.54
     flux
    0.53
     hydraulic
    0.52
     dispersion
    0.52
     thermal
    0.52
     heats
    0.52
     shafts
    0.51
    Activations Density 32.722%

    No Known Activations