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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3795
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically those related to web development involving scrolling, style and Javascript

    oai_token-act-pair · gemini-2.0-flash

    HTML/web code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     defaultstate
    -0.82
    +#+
    -0.73
    <_>
    -0.56
     Exacts
    -0.55
    <bos>
    -0.55
    تقاوى
    -0.54
     katk
    -0.54
     RIPRODUZIONE
    -0.53
    WithIOException
    -0.52
    sii
    -0.52
    POSITIVE LOGITS
     lenker
    0.60
     remercier
    0.59
     efficacement
    0.57
     efectivamente
    0.56
     poète
    0.56
    WebControls
    0.56
     avanti
    0.55
     என்று
    0.53
     CiNii
    0.52
    oprecipitation
    0.52
    Activations Density 1.658%

    No Known Activations