© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12503
    Prev
    Next
    INDEX
    Explanations

    HTML code defining row and column classes, including potentially the number 1 or 2 in the definitions

    oai_token-act-pair · gemini-2.0-flash

    col

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     col
    -0.69
    col
    -0.65
     Col
    -0.54
    Col
    -0.54
    colos
    -0.47
    tre
    -0.46
     er
    -0.45
    <bos>
    -0.45
    t
    -0.45
     pos
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.79
    TargetException
    0.79
    UseVisualStyle
    0.75
    MLLoader
    0.75
     مشين
    0.75
    ^(@)
    0.71
    :✨
    0.70
    ="@+
    0.69
     BorderSide
    0.69
    ValueStyle
    0.66
    Activations Density 0.425%

    No Known Activations