© 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. 2971
    Prev
    Next
    INDEX
    Explanations

    code snippets (likely C# and Go) with a focus on variable declarations, data types, and control flow elements

    oai_token-act-pair · gemini-2.0-flash

    say string

    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
    String
    -1.51
     String
    -1.49
     Strings
    -0.70
    exitRule
    -0.67
     strings
    -0.61
    NSString
    -0.59
    makeText
    -0.58
    reportWebVitals
    -0.56
    QString
    -0.55
    orace
    -0.55
    POSITIVE LOGITS
     cuchar
    0.53
     avulla
    0.50
    Geplaatst
    0.50
    itemBuilder
    0.47
    #__
    0.46
    wasn
    0.45
     lentement
    0.44
     letto
    0.44
     cuero
    0.44
     juges
    0.43
    Activations Density 0.943%

    No Known Activations