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. 1591
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with expertise and research

    oai_token-act-pair · gemini-2.0-flash

    expert opinions and research

    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
     expert
    -2.69
    Expert
    -2.58
     Expert
    -2.50
    expert
    -2.44
     experts
    -2.38
     Experts
    -2.30
    Experts
    -2.28
     EXPERT
    -2.22
     specialist
    -2.13
    experts
    -2.09
    POSITIVE LOGITS
     Mémoires
    0.54
    endaftaran
    0.54
    mybatisplus
    0.54
    nomin
    0.50
    foni
    0.50
    AndEndTag
    0.49
    oulli
    0.48
     légale
    0.47
    ikai
    0.47
     Derechos
    0.47
    Activations Density 1.471%

    No Known Activations