© 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. 10671
    Prev
    Next
    INDEX
    Explanations

    text about Beverly Ridge, LA and other high end locations

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or exceptions

    np_token-act-pair-logits · gpt-4o-mini
    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
     فريبيس
    -0.50
    abank
    -0.49
    ņš
    -0.46
    первых
    -0.46
    peto
    -0.45
     miro
    -0.44
     linear
    -0.44
     luật
    -0.44
     transfieras
    -0.43
    ungkapkan
    -0.43
    POSITIVE LOGITS
    MessageTagHelper
    0.73
    yntaxException
    0.66
    AntiForgeryToken
    0.60
     चीज़ों
    0.58
    SharedDtor
    0.57
    fillType
    0.56
    зулта
    0.56
     nakalista
    0.56
    دانشنامهٔ
    0.54
    arschu
    0.54
    Activations Density 0.788%

    No Known Activations