© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    code snippets, labels, and identifiers denoted with the letter 'q' followed by other characters or numbers

    oai_token-act-pair · gemini-2.0-flash

    q

    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
    ngdoc
    -0.66
     onCreateView
    -0.64
    webElementXpaths
    -0.62
     consultato
    -0.59
     ***!
    -0.57
    ContentAsync
    -0.56
    a
    -0.54
     dataSnapshot
    -0.54
    ysław
    -0.54
    GeneratedMessage
    -0.54
    POSITIVE LOGITS
    Personensuche
    0.52
     мәкал
    0.49
    Televis
    0.48
    umentación
    0.43
     bezeichneter
    0.42
    entgen
    0.42
     Grims
    0.41
    mployment
    0.41
     commod
    0.40
     Asbury
    0.40
    Activations Density 1.664%

    No Known Activations