© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7427
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, particularly ones used when building or manipulating data structures, especially in go and python

    oai_token-act-pair · gemini-2.0-flash

    Code and library imports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.60
    int
    -0.59
     [
    -0.55
     
    -0.53
    ;
    -0.53
    [
    -0.53
    <eos>
    -0.52
    me
    -0.52
    de
    -0.51
     (
    -0.51
    POSITIVE LOGITS
     EconPapers
    1.10
    TagHelper
    1.10
     المعيارى
    1.09
    \{\\
    1.03
    VersionUID
    1.00
    TagMode
    0.98
     تانيه
    0.97
     myſelf
    0.96
     Theſe
    0.95
     виправивши
    0.94
    Activations Density 1.375%

    No Known Activations