© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4039
    Prev
    Next
    INDEX
    Explanations

    words commonly used in technical documents, perhaps code or medical papers

    oai_token-act-pair · gemini-2.0-flash

    scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     censiti
    -0.78
    tonode
    -0.68
     للمعارف
    -0.67
    Hentet
    -0.63
     noten
    -0.63
    — 
    -0.61
    Rüyada
    -0.60
    writeFieldEnd
    -0.60
    MISSIONS
    -0.59
    ergies
    -0.59
    POSITIVE LOGITS
    <bos>
    1.01
     blanches
    0.46
     Ahnung
    0.43
     obviously
    0.43
     känd
    0.42
    __);
    0.42
     évit
    0.41
     attentes
    0.41
     tentu
    0.41
     acceder
    0.41
    Activations Density 9.520%

    No Known Activations