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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11059
    Prev
    Next
    INDEX
    Explanations

    scientific measurements, especially in oceanography, including units, numbers, and instruments

    oai_token-act-pair · gemini-2.0-flash

    terms related to containers or tanks in scientific context

    np_token-act-pair-logits · gpt-4o-mini

    Aquariums/water tanks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
    底
    -0.56
    asties
    -0.46
     issue
    -0.42
    Примечания
    -0.42
    orced
    -0.42
    ケル
    -0.42
    算
    -0.42
    bero
    -0.42
    mey
    -0.42
    hbar
    -0.41
    POSITIVE LOGITS
    SourceChecksum
    0.98
    StoryboardSegue
    0.93
    extAlignment
    0.88
     <=",
    0.81
     MainAxisSize
    0.79
     ब्रेकडाउन
    0.75
     Tanks
    0.75
     tanks
    0.74
     tank
    0.72
    MemoryWarning
    0.70
    Activations Density 1.564%

    No Known Activations