© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9264
    Prev
    Next
    INDEX
    Explanations

    code snippets, addresses, or recipes involving food

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oa̍t
    -0.78
    CompleteListener
    -0.67
    tagHelperRunner
    -0.66
     leçons
    -0.61
     oreilles
    -0.59
    avyzd
    -0.58
     Chaldean
    -0.58
    رشف
    -0.58
    enumii
    -0.57
     répondu
    -0.57
    POSITIVE LOGITS
     onCreateView
    0.50
     Py
    0.48
    UnknownFields
    0.48
     становника
    0.46
    '])){
    0.45
     createState
    0.45
     <>",
    0.45
     Pyle
    0.45
     Institution
    0.44
     eventdata
    0.43
    Activations Density 5.599%

    No Known Activations