© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8155
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly C++ and Java, identifying variable declarations, object instantiations, and function definitions, particularly those related to names, numbers, ages, animals, and categories

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    دانشنامهٔ
    -0.65
     onPostExecute
    -0.65
    :✨
    -0.63
     مرئيه
    -0.63
     autorytatywna
    -0.61
    ArgsConstructor
    -0.60
     propOrder
    -0.56
    fromnode
    -0.53
     betweenstory
    -0.53
     Seeder
    -0.53
    POSITIVE LOGITS
    URLException
    0.58
    Hur
    0.49
     initComponents
    0.47
    WidgetItem
    0.47
    жах
    0.47
    TabLayout
    0.46
    }{*}{
    0.46
    aliyun
    0.46
     inteiro
    0.46
    eterangan
    0.45
    Activations Density 0.305%

    No Known Activations