© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15439
    Prev
    Next
    INDEX
    Explanations

    json data structures with pagination information, often including URLs

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    code snippets and parameters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ujednoznacz
    -0.47
    skis
    -0.46
    isDebugEnabled
    -0.45
    assertIn
    -0.43
    Története
    -0.43
     chauffe
    -0.42
    racene
    -0.42
     Ran
    -0.42
    してお
    -0.41
     mAh
    -0.41
    POSITIVE LOGITS
    BeginContext
    0.71
     autorytatywna
    0.63
     AppCompatTheme
    0.59
     records
    0.59
     חיצוניים
    0.59
     препратки
    0.59
     Etter
    0.58
     ویکی‌پدی
    0.57
    RTGC
    0.56
    records
    0.56
    Activations Density 2.347%

    No Known Activations