© 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. 15398
    Prev
    Next
    INDEX
    Explanations

    code-related texts, specifically code that uses the dot operator to access object properties or methods

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or functions

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

    code snippets

    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
     للمعارف
    -0.71
    ьаж
    -0.67
    Personendaten
    -0.57
    omeness
    -0.55
    رشف
    -0.54
    الإنجليزية
    -0.54
    FailureListener
    -0.54
     BnF
    -0.52
    createTextNode
    -0.52
    getItemId
    -0.51
    POSITIVE LOGITS
    клопе
    0.53
     Audiodateien
    0.52
     convertView
    0.50
    Feng
    0.47
     {?>
    0.47
    ExtendWith
    0.46
    putAll
    0.45
     فريبيس
    0.45
     grátis
    0.45
    EXE
    0.45
    Activations Density 0.245%

    No Known Activations