© 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. 4516
    Prev
    Next
    INDEX
    Explanations

    terms related to politics, government, and organizations

    oai_token-act-pair · gemini-2.0-flash

    former

    np_max-act · 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
     former
    -2.20
    Former
    -2.08
     Former
    -1.94
    former
    -1.94
     ehemaligen
    -1.48
     ehemalige
    -1.45
     býval
    -1.30
     mantan
    -1.20
     ehemal
    -1.15
     früheren
    -1.08
    POSITIVE LOGITS
    migrationBuilder
    0.59
     بيها
    0.54
    httphttps
    0.52
    GEBURTS
    0.51
     remont
    0.49
    buk
    0.49
     recevrez
    0.49
    trze
    0.48
    rawDesc
    0.48
    ecio
    0.48
    Activations Density 11.113%

    No Known Activations