© 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. 9334
    Prev
    Next
    INDEX
    Explanations

    verbs conjugated in what appears to be a Romance language

    oai_token-act-pair · 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
     we
    -0.73
     I
    -0.58
     jsme
    -0.55
     мы
    -0.54
    amos
    -0.53
    ,
    -0.53
     We
    -0.52
     du
    -0.51
    ↵
    -0.50
     Z
    -0.49
    POSITIVE LOGITS
     defaultstate
    1.00
     itſelf
    0.91
    تقاوى
    0.87
     >=",
    0.75
    potranspiration
    0.74
    expandindo
    0.72
     emailAlready
    0.71
    SourceChecksum
    0.70
     propOrder
    0.69
    }{*}{}
    0.68
    Activations Density 4.604%

    No Known Activations