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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1099
    Prev
    Next
    INDEX
    Explanations

    various characters and keywords used in programming languages, especially semicolons, access modifiers like public and private, angle brackets, and class names relating to data storage or transfer

    oai_token-act-pair · gemini-2.0-flash

    code

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

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
     result
    -0.42
    crollView
    -0.42
     للمعارف
    -0.41
    Xna
    -0.39
    Gweler
    -0.39
     Lightboxes
    -0.39
    ależy
    -0.38
     Re
    -0.38
     re
    -0.38
     Off
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.80
     تضيفلها
    0.78
    RegistryLite
    0.77
     Majefty
    0.76
     preſent
    0.76
    StructEnd
    0.75
     ſta
    0.74
     houſe
    0.72
     ſmall
    0.72
     ſever
    0.71
    Activations Density 1.188%

    No Known Activations