© 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. 466
    Prev
    Next
    INDEX
    Explanations

    code and programming terminology

    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
     betweenstory
    -0.83
    oredCriteria
    -0.81
    NOPQRST
    -0.80
    WebElementEntity
    -0.76
    parsedMessage
    -0.75
     Roskov
    -0.73
    hdashline
    -0.73
    fjspx
    -0.68
    hasMoreElements
    -0.68
    tvguidetime
    -0.67
    POSITIVE LOGITS
     Chal
    0.40
    SupportActionBar
    0.40
     torner
    0.39
    ък
    0.39
    {@
    0.39
     Coron
    0.39
    rood
    0.38
    AddTagHelper
    0.38
    Fris
    0.38
    マ
    0.38
    Activations Density 9.644%

    No Known Activations