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. 13901
    Prev
    Next
    INDEX
    Explanations

    the string "Ant" followed by a variety of characters

    oai_token-act-pair · gemini-2.0-flash

    ant

    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
     protoimpl
    -0.54
    eryn
    -0.52
     BUREAU
    -0.52
     ammon
    -0.49
     Amon
    -0.49
     متعلقه
    -0.49
    findpost
    -0.48
     CreateTagHelper
    -0.48
     Bureau
    -0.47
     Meyer
    -0.47
    POSITIVE LOGITS
    makeConstraints
    0.56
     GenerationType
    0.56
    AccessorTable
    0.54
     ddelweddau
    0.53
    исленность
    0.52
     ContentValues
    0.52
    WriteAttribute
    0.50
    abetes
    0.49
    ficulties
    0.49
     Wikisource
    0.48
    Activations Density 0.315%

    No Known Activations