© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10027
    Prev
    Next
    INDEX
    Explanations

    file paths, especially those related to python files and shared libraries

    oai_token-act-pair · gemini-2.0-flash

    forward slash

    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
    Чыганаклар
    -0.56
    <bos>
    -0.56
    ">—
    -0.52
    Примітки
    -0.49
    olov
    -0.48
     Nähe
    -0.48
     fuer
    -0.47
    Хьажоргаш
    -0.47
    XmlAccessorType
    -0.46
    qrstuvwxyz
    -0.46
    POSITIVE LOGITS
    IsMutable
    0.77
     bezeichneter
    0.61
     insuffisamment
    0.57
    EndGlobalSection
    0.57
    tablissements
    0.54
    LElement
    0.54
     autorytatywna
    0.54
    ########.
    0.53
    greSQL
    0.53
    Typing
    0.52
    Activations Density 9.241%

    No Known Activations