© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9333
    Prev
    Next
    INDEX
    Explanations

    words related to javascript programming

    oai_token-act-pair · gemini-2.0-flash

    coding data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.58
    FTFY
    -0.55
    contentLoaded
    -0.52
     BorderSide
    -0.48
     StringTokenizer
    -0.46
     Exactos
    -0.45
     Sü
    -0.45
    र्फ
    -0.45
      (
    -0.45
    /−
    -0.43
    POSITIVE LOGITS
     AssemblyCompany
    0.60
     ++)
    0.59
    جوايز
    0.56
    señor
    0.56
    存于互联网档案馆
    0.56
    <bos>
    0.55
    stdc
    0.52
    Filmo
    0.50
     perten
    0.49
     classement
    0.48
    Activations Density 25.573%

    No Known Activations