© 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. 7975
    Prev
    Next
    INDEX
    Explanations

    math and computer code snippets

    oai_token-act-pair · gemini-2.0-flash

    Mathematical symbols

    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
     autorytatywna
    -0.85
     ProtoMessage
    -0.85
    DockStyle
    -0.78
    CppMethod
    -0.76
    awtextra
    -0.74
     doInBackground
    -0.72
    AnimationsModule
    -0.71
    findpost
    -0.70
    RegistryLite
    -0.68
     ***!
    -0.67
    POSITIVE LOGITS
    appé
    0.63
    })->
    0.61
    InteropServices
    0.57
    (;;)
    0.54
     Erle
    0.53
    WidgetItem
    0.53
     ordinario
    0.52
    óság
    0.52
     kHz
    0.52
    renço
    0.50
    Activations Density 1.452%

    No Known Activations