© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4217
    Prev
    Next
    INDEX
    Explanations

    the word "light", often in the context of an invention, product description, or metaphor

    oai_token-act-pair · gemini-2.0-flash

    light

    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
     civiles
    -0.52
    ترنت
    -0.51
    RefNanny
    -0.49
     rodillas
    -0.48
    InjectAttribute
    -0.47
     незавершена
    -0.47
     prestaciones
    -0.46
     урна
    -0.46
     voglio
    -0.46
     esquina
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.75
    ModelAdmin
    0.66
     Photocase
    0.65
     EconPapers
    0.65
    Filmografie
    0.59
    latego
    0.59
     faſt
    0.58
     sleepers
    0.58
    AnchorTagHelper
    0.57
    yarnpkg
    0.57
    Activations Density 2.525%

    No Known Activations