© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2904
    Prev
    Next
    INDEX
    Explanations

    snippets of code, especially JSON-like structures

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    "
    -0.75
    -
    -0.71
    (
    -0.71
    {
    -0.65
    
    -0.63
    *
    -0.63
    )
    -0.60
    [
    -0.58
    '
    -0.57
    $
    -0.57
    POSITIVE LOGITS
     étoit
    0.71
     démocr
    0.70
     Monfieur
    0.69
     hindurch
    0.69
    InputBorder
    0.69
    antaranya
    0.68
    RectangleBorder
    0.68
     automatiques
    0.66
    <?
    0.66
     étoient
    0.65
    Activations Density 5.930%

    No Known Activations