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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14186
    Prev
    Next
    INDEX
    Explanations

    code snippets and descriptions of camera and object positioning and rotation

    oai_token-act-pair · gemini-2.0-flash

    coordinate space

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    mybatisplus
    -0.66
    UnknownFieldSet
    -0.66
    WithMany
    -0.66
    ContentAsync
    -0.65
    
    -0.60
    évaluateur
    -0.56
    NewUrlParser
    -0.53
     orgull
    -0.53
     MediatR
    -0.53
     parseFrom
    -0.47
    POSITIVE LOGITS
     coordinate
    0.70
     space
    0.69
     frame
    0.67
    bietern
    0.64
     coordinates
    0.61
     representation
    0.60
    pace
    0.58
     domain
    0.57
     basis
    0.57
    coordinate
    0.57
    Activations Density 3.334%

    No Known Activations