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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12079
    Prev
    Next
    INDEX
    Explanations

    the word "of" near words like "the," "all," and pronouns

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     uVar
    -0.63
    новниш
    -0.62
    nella
    -0.61
    felves
    -0.59
    ỡng
    -0.59
    yonel
    -0.58
    ніципа
    -0.56
    hésitez
    -0.55
    twimg
    -0.54
    Ҭ
    -0.54
    POSITIVE LOGITS
     of
    0.77
     CreateTagHelper
    0.56
    of
    0.51
    Glej
    0.51
     }}"></
    0.47
     Cæsar
    0.41
    migrationBuilder
    0.40
     Of
    0.40
    ́ng
    0.39
     use
    0.39
    Activations Density 6.132%

    No Known Activations