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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7044
    Prev
    Next
    INDEX
    Explanations

    terms describing relationships or differences between two things

    oai_token-act-pair · gemini-2.0-flash

    Biology and scientific concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     pair
    -0.50
     preferentially
    -0.49
    pair
    -0.47
     pairs
    -0.47
    han
    -0.46
    artes
    -0.43
    unan
    -0.42
    相手
    -0.42
    つもり
    -0.41
    iber
    -0.41
    POSITIVE LOGITS
    存于互联网档案馆
    0.77
    RectangleBorder
    0.76
    
    0.74
     kaarangay
    0.73
    
    0.70
     surla
    0.69
     nahilalakip
    0.68
    TagMode
    0.67
    OrNil
    0.67
     MainAxisSize
    0.66
    Activations Density 3.762%

    No Known Activations