© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11709
    Prev
    Next
    INDEX
    Explanations

    html div tags

    oai_token-act-pair · gemini-2.0-flash

    div

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    div
    -2.50
    Div
    -1.98
     Div
    -1.91
     div
    -1.89
    DIV
    -1.64
     DIV
    -1.61
     divid
    -1.14
     divis
    -1.13
     divi
    -1.13
     division
    -1.11
    POSITIVE LOGITS
    ViewFeatures
    0.84
     CreateTagHelper
    0.82
    Manbalar
    0.67
    Hochspringen
    0.62
    LLocation
    0.58
     preſent
    0.58
     كومونز
    0.58
     Италијани
    0.57
    uthor
    0.57
    脚注の使い方
    0.56
    Activations Density 0.506%

    No Known Activations