© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9632
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code snippets, particularly those related to webpage formatting and form elements

    oai_token-act-pair · gemini-2.0-flash

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.01
    #
    -0.77
    таратура
    -0.74
    IntoConstraints
    -0.66
    HideFlags
    -0.63
    PhysRevLett
    -0.63
    utilisons
    -0.62
    WebElementEntity
    -0.62
    class
    -0.61
    rzez
    -0.61
    POSITIVE LOGITS
     rapport
    0.57
     Port
    0.48
    ?')
    0.47
     Kolo
    0.47
    tong
    0.44
    ---*/
    0.44
    essi
    0.44
     vast
    0.43
    perg
    0.43
     fus
    0.43
    Activations Density 1.552%

    No Known Activations