© 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. 15472
    Prev
    Next
    INDEX
    Explanations

    words associated with research papers and technical documents, especially related to computer science

    oai_token-act-pair · gemini-2.0-flash

    systems features

    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
    Переваги
    -0.60
    Sucesor
    -0.59
     bezeichneter
    -0.54
    domada
    -0.51
    はじめに
    -0.47
     استنادى
    -0.47
    mare
    -0.46
     Guwahati
    -0.46
    <bos>
    -0.46
     subspecies
    -0.46
    POSITIVE LOGITS
    XmlAccessorType
    0.60
     CreateTagHelper
    0.55
    DotNetBar
    0.52
     '\\;'
    0.52
    migrationBuilder
    0.52
    évaluateur
    0.51
     createSlice
    0.51
    AndroidJUnit
    0.50
     autorytatywna
    0.50
     fair
    0.49
    Activations Density 0.721%

    No Known Activations