© 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. 4527
    Prev
    Next
    INDEX
    Explanations

    phrases related to logical addition of items or ideas.

    oai_token-act-pair · gemini-2.0-flash

    codes

    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
    <bos>
    -1.07
    RegressionTest
    -0.89
     mergeFrom
    -0.80
     ویکی‌پدی
    -0.73
    rrbracket
    -0.71
     AspNetCore
    -0.71
    Autoritní
    -0.71
     saites
    -0.70
     pinulongan
    -0.70
    Spoljašnje
    -0.68
    POSITIVE LOGITS
     حی
    0.55
     doInBackground
    0.54
    prepareStatement
    0.47
    FontStyle
    0.46
    ↵↵↵
    0.45
     mystérie
    0.42
    ربعة
    0.42
     rodin
    0.42
     possibilités
    0.41
    /></
    0.41
    Activations Density 1.510%

    No Known Activations