© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13423
    Prev
    Next
    INDEX
    Explanations

    the word "make" and the phrase "custom-made".

    oai_token-act-pair · gemini-2.0-flash

    Make

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    TintMode
    -1.07
     تانيه
    -0.95
    writeField
    -0.86
    ionario
    -0.85
    AnimationsModule
    -0.81
    onAttach
    -0.79
     تضيفلها
    -0.79
    省市镇
    -0.78
    setVerticalGroup
    -0.77
    tonsoft
    -0.76
    POSITIVE LOGITS
     bety
    0.52
    ungkinkan
    0.45
    ?>
    0.43
    tfrac
    0.43
    WriteLiteral
    0.43
     soins
    0.43
     epoca
    0.43
     Komisi
    0.43
    !("
    0.42
     lyst
    0.42
    Activations Density 0.146%

    No Known Activations