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. 1145
    Prev
    Next
    INDEX
    Explanations

    sales and technology marketing language, with pricing or calls to action

    oai_token-act-pair · gemini-2.0-flash

    technical words found on websites

    np_token-act-pair-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
    ərb
    -0.56
     externi
    -0.54
    igshid
    -0.52
    nonatomic
    -0.51
    atification
    -0.50
    geord
    -0.49
     onBind
    -0.49
    modelBuilder
    -0.47
    arder
    -0.47
    ropa
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.72
    AddHtmlAttribute
    0.71
     specializing
    0.54
     safest
    0.53
     faſt
    0.53
     beſt
    0.52
    AddTagHelper
    0.52
     propOrder
    0.52
    Espèce
    0.50
    opcional
    0.50
    Activations Density 1.753%

    No Known Activations