© 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. 463
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical phrases

    oai_token-act-pair · gemini-2.0-flash

    number

    np_max-act · 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
    ing
    -0.50
    خصة
    -0.45
     razie
    -0.44
    oubted
    -0.44
    kend
    -0.44
    IOException
    -0.42
    owice
    -0.40
    issors
    -0.40
    ormick
    -0.39
     case
    -0.39
    POSITIVE LOGITS
    ########.
    0.93
    
    0.79
    '])){
    0.77
    BeginInit
    0.77
    ]='\
    0.75
    AddHtmlAttribute
    0.75
    ="@+
    0.73
    migrationBuilder
    0.73
    GenerationType
    0.71
     snippetHide
    0.71
    Activations Density 1.277%

    No Known Activations