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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16346
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical or electrical components/processes.

    oai_token-act-pair · gemini-2.0-flash

    technical/mechanical descriptions

    np_token-act-pair-logits · gemini-2.0-flash

    mechanical parts engaging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    GIVEREF
    -0.65
    
    -0.64
     للمعارف
    -0.64
     courir
    -0.57
    awtextra
    -0.56
     inconnu
    -0.51
     Савезне
    -0.50
     culturelle
    -0.50
     HttpNotFound
    -0.50
    StoryboardSegue
    -0.49
    POSITIVE LOGITS
    setContentView
    0.58
    astéro
    0.52
    bodyParser
    0.51
    lished
    0.49
     rej
    0.47
     actes
    0.46
     license
    0.46
    इट
    0.45
    adu
    0.45
    resz
    0.45
    Activations Density 3.557%

    No Known Activations