© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 457
    Prev
    Next
    INDEX
    Explanations

    code and punctuation

    oai_token-act-pair · gemini-2.0-flash

    Code-related tokens

    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
    Negative Logits
     full
    -0.59
     pair
    -0.51
     force
    -0.50
     forces
    -0.47
     Full
    -0.46
     lắm
    -0.45
    etch
    -0.45
     IMM
    -0.45
     Cre
    -0.44
    atti
    -0.44
    POSITIVE LOGITS
    
    0.85
    AddTagHelper
    0.83
    Parcelize
    0.81
     للاسماء
    0.81
     AssemblyCulture
    0.78
    ChildScrollView
    0.75
    ंदीखरीदारी
    0.73
    MemoryWarning
    0.71
     OnInit
    0.69
     المعيارى
    0.69
    Activations Density 1.865%

    No Known Activations