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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4703
    Prev
    Next
    INDEX
    Explanations

    file paths related to Python code libraries

    oai_token-act-pair · gemini-2.0-flash

    code snippets or programming functions

    np_token-act-pair-logits · gpt-4o-mini

    Python package installation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    +#+
    -0.71
    لينكات
    -0.67
    ChildScrollView
    -0.66
    GEBURTS
    -0.65
    posedge
    -0.63
     useAppContext
    -0.60
     Cataloging
    -0.59
     Crusoe
    -0.57
    Дереккөздер
    -0.57
     חיצוניים
    -0.57
    POSITIVE LOGITS
    RunWith
    0.63
    ledo
    0.45
    utriche
    0.44
    SaveChangesAsync
    0.43
    <tbody>
    0.43
     lief
    0.42
    Sprintf
    0.41
     pick
    0.41
    ivity
    0.40
     ombro
    0.39
    Activations Density 1.419%

    No Known Activations