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. 16143
    Prev
    Next
    INDEX
    Explanations

    initials

    oai_token-act-pair · gemini-2.0-flash

    Author initials in citations

    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
    endsection
    -0.63
    jsonwebtoken
    -0.60
    #
    -0.57
    putAll
    -0.56
     otomatig
    -0.55
    WebElementEntity
    -0.55
    Parcelize
    -0.55
    rably
    -0.54
    Sucesor
    -0.54
    MigrationBuilder
    -0.53
    POSITIVE LOGITS
     H
    0.51
     W
    0.50
    ANDUM
    0.48
    harusnya
    0.47
     A
    0.45
     namanya
    0.44
     P
    0.44
    Introductory
    0.44
     M
    0.43
     året
    0.42
    Activations Density 2.256%

    No Known Activations