© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14036
    Prev
    Next
    INDEX
    Explanations

    specific technical wording related to light and exposure, often in the context of manufacturing or measurement.

    oai_token-act-pair · gemini-2.0-flash

    light and optics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    المناصب
    -0.73
    ConstraintMaker
    -0.68
    Portail
    -0.60
     elétrico
    -0.60
    Jeografia
    -0.59
     JpaRepository
    -0.58
    writerow
    -0.57
    tanleria
    -0.57
    بوابة
    -0.56
    setupUi
    -0.56
    POSITIVE LOGITS
    ubri
    0.56
     mor
    0.54
    уза
    0.50
    phology
    0.50
     soft
    0.49
    Hauptartikel
    0.48
    VISIBLE
    0.48
     blue
    0.47
    Lähteet
    0.47
     white
    0.45
    Activations Density 2.327%

    No Known Activations