© 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. 15381
    Prev
    Next
    INDEX
    Explanations

    the word "Sith" and the word "define" in code snippets and legal documents

    oai_token-act-pair · gemini-2.0-flash

    Sith

    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
    Not in Any Lists

    No Comments

    Negative Logits
     вікі
    -0.59
    ❉
    -0.54
    Portail
    -0.52
    RegressionTest
    -0.51
    Vidite
    -0.50
    EndProject
    -0.50
    зулта
    -0.49
    Demografie
    -0.49
    ürme
    -0.49
     sẻ
    -0.49
    POSITIVE LOGITS
     Exacts
    0.66
    IsContent
    0.64
    enumi
    0.60
    tagHelperRunner
    0.58
    帖最后由
    0.57
     فريبيس
    0.57
     ulang
    0.54
    makeConstraints
    0.54
     AssemblyCompany
    0.53
     antaranya
    0.53
    Activations Density 0.031%

    No Known Activations