© 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. 9787
    Prev
    Next
    INDEX
    Explanations

    words used in legal and bureaucratic contexts, sometimes in reference to conflicts, agreements, or organizations

    oai_token-act-pair · gemini-2.0-flash

    with

    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
    UnitTesting
    -0.77
     Houſe
    -0.70
     Majefty
    -0.67
     himſelf
    -0.65
    mybatisplus
    -0.65
     Jefus
    -0.60
    inerja
    -0.60
     enfans
    -0.59
    jaardag
    -0.59
     themſelves
    -0.58
    POSITIVE LOGITS
    новниш
    0.73
     насеље
    0.64
    verdi
    0.57
    ništ
    0.55
     mxArray
    0.53
    CardBody
    0.52
    MathML
    0.52
    CodeDom
    0.51
    blut
    0.51
    ########.
    0.49
    Activations Density 6.023%

    No Known Activations