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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10998
    Prev
    Next
    INDEX
    Explanations

    words or short phrases associated with education and philanthropy

    oai_token-act-pair · gemini-2.0-flash

    technical terminology or specialized language

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

    education and technology

    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
    IBAction
    -0.50
    OrBuilder
    -0.48
    日閲覧
    -0.46
     Daß
    -0.45
     parents
    -0.45
     فريبيس
    -0.45
    Manbalar
    -0.44
     kağı
    -0.44
     registers
    -0.44
     phosphates
    -0.44
    POSITIVE LOGITS
    tonsoft
    0.61
    SerializedSize
    0.56
    AddHtmlAttribute
    0.53
    thâu
    0.52
     للاسماء
    0.50
     AssemblyProduct
    0.50
    StructEnd
    0.50
     zewnętrzne
    0.49
     ва
    0.48
    lgica
    0.48
    Activations Density 0.451%

    No Known Activations