© 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. 2884
    Prev
    Next
    INDEX
    Explanations

    code like constructs such as `def`, `all`, `module`, `parse`, and `vector`.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    WithIOException
    -0.98
    WriteTagHelper
    -0.81
    tagHelperRunner
    -0.77
     myſelf
    -0.74
    TagMode
    -0.73
     ExecuteAsync
    -0.73
    EDEFAULT
    -0.71
    تقاوى
    -0.70
    AsUp
    -0.70
     VIAF
    -0.69
    POSITIVE LOGITS
    endphp
    0.58
    RegressionTest
    0.54
     routine
    0.46
     structures
    0.44
     structure
    0.44
     seien
    0.44
    [--
    0.43
    Procedures
    0.43
    Procedure
    0.40
    InputModule
    0.40
    Activations Density 3.502%

    No Known Activations