© 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. 4289
    Prev
    Next
    INDEX
    Explanations

    terms used to analyze data using mathematical models

    oai_token-act-pair · gemini-2.0-flash

    treat

    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
    Not in Any Lists

    No Comments

    Negative Logits
     treats
    -1.03
     treat
    -0.97
     treated
    -0.89
     treating
    -0.82
     Treat
    -0.82
    Treat
    -0.79
    treat
    -0.78
     Treats
    -0.77
     Treated
    -0.76
     TREAT
    -0.71
    POSITIVE LOGITS
    MessageDigest
    0.58
     isbn
    0.54
    OutOfBounds
    0.54
     Another
    0.52
     collier
    0.50
     Suivez
    0.49
     ویکی‌پدیای
    0.49
     Otra
    0.49
    PutMapping
    0.48
     poffible
    0.47
    Activations Density 12.817%

    No Known Activations