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. 14439
    Prev
    Next
    INDEX
    Explanations

    instances where something comes to mind, especially in the context of Java code or programming issues

    oai_token-act-pair · gemini-2.0-flash

    variations of "come"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.66
    quelize
    -0.63
    agisse
    -0.60
    GEBURTS
    -0.57
    SBATCH
    -0.56
     GreatSchools
    -0.52
     Theſe
    -0.52
    actionMode
    -0.51
     Forumite
    -0.51
     BorderRadius
    -0.51
    POSITIVE LOGITS
     comes
    1.91
     come
    1.83
     Come
    1.55
    come
    1.55
    comes
    1.54
     Comes
    1.53
    Come
    1.47
     COMES
    1.46
    Comes
    1.43
     spring
    1.41
    Activations Density 0.674%

    No Known Activations