© 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. 9490
    Prev
    Next
    INDEX
    Explanations

    words that end in letters such as "ing," "ed," "able," "al," "ion," "us", and starts with letters such as "enter" or "gene."

    oai_token-act-pair · gemini-2.0-flash

    entertainment

    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
     briefly
    -1.00
     brief
    -0.99
    brief
    -0.96
    Brief
    -0.89
     Brief
    -0.88
     Waray
    -0.85
    RectangleBorder
    -0.82
     entertainment
    -0.77
    BRIEF
    -0.77
     BRIEF
    -0.76
    POSITIVE LOGITS
     برانيه
    0.47
    არი
    0.43
    urlpatterns
    0.42
    e
    0.40
     empe
    0.40
     liitty
    0.40
    autogui
    0.40
    eqn
    0.40
     entscheid
    0.39
    straat
    0.38
    Activations Density 10.033%

    No Known Activations