© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9383
    Prev
    Next
    INDEX
    Explanations

    words related to research, analysis, and technical writing.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aarrggbb
    -0.84
    ,:),
    -0.72
    Vidite
    -0.72
     Normdatei
    -0.70
    脚注の使い方
    -0.70
    Referanser
    -0.64
     linkovi
    -0.63
     pinulongan
    -0.63
    Ծանոթ
    -0.62
    الإنجليزية
    -0.61
    POSITIVE LOGITS
    cstdlib
    0.56
    naught
    0.52
     franquicia
    0.49
     mitos
    0.49
    ี้ยง
    0.48
    ANTAGES
    0.46
    ggplot
    0.46
    spunk
    0.46
    HomeAsUpEnabled
    0.45
     durabilidad
    0.44
    Activations Density 13.101%

    No Known Activations