© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 300
    Prev
    Next
    INDEX
    Explanations

    code, particularly C or C++, along with file system and memory management functions

    oai_token-act-pair · gemini-2.0-flash

    underscore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ^(@)
    -0.59
    ParallelGroup
    -0.58
    ocardial
    -0.52
    DispatchToProps
    -0.51
    SequentialGroup
    -0.50
    forName
    -0.49
    fore
    -0.49
    AttributeSet
    -0.48
    AllowUser
    -0.48
    VersionUID
    -0.47
    POSITIVE LOGITS
     թվական
    0.57
     ویکی‌پدیا
    0.54
    stick
    0.52
    setupUi
    0.51
    publique
    0.51
    larna
    0.50
     Korn
    0.50
     Lund
    0.50
    omi
    0.49
     HttpStatus
    0.49
    Activations Density 6.491%

    No Known Activations