© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3617
    Prev
    Next
    INDEX
    Explanations

    code snippets with the term "driver" and action verbs like "click"

    oai_token-act-pair · gemini-2.0-flash

    driver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Normdatei
    -0.98
     CreateTagHelper
    -0.94
    AndroidJUnit
    -0.90
    rungsseite
    -0.87
     Chwiliwch
    -0.84
    jspx
    -0.83
    الحياه
    -0.83
    zzleHttp
    -0.81
     فريبيس
    -0.81
    ftagPool
    -0.81
    POSITIVE LOGITS
    <eos>
    0.48
    beitrag
    0.41
    bourg
    0.38
     مقابل
    0.38
    mon
    0.38
     daž
    0.38
    ɜ
    0.37
    dė
    0.37
     стены
    0.37
     né
    0.36
    Activations Density 9.477%

    No Known Activations