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. 14759
    Prev
    Next
    INDEX
    Explanations

    a mix of Facebook account-related terms, Croatian language related to account verification, and possible C# programming language terms

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    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
    ⓘ
    -0.59
    MutableLiveData
    -0.49
     AssemblyCulture
    -0.47
    LayoutConstraint
    -0.47
     FMI
    -0.43
     AppModule
    -0.42
    ited
    -0.41
    typeorm
    -0.41
    Biographie
    -0.40
    Carriera
    -0.40
    POSITIVE LOGITS
    PMailer
    0.63
    TypedDataSet
    0.60
     utafitiHapana
    0.59
    存于互联网档案馆
    0.57
     jScrollPane
    0.57
     okol
    0.55
    jspb
    0.54
    >//
    0.54
    damente
    0.53
    AnchorStyles
    0.52
    Activations Density 0.405%

    No Known Activations