© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12411
    Prev
    Next
    INDEX
    Explanations

    the keyword "class" and related terms used in programming languages

    oai_token-act-pair · gemini-2.0-flash

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    出版年
    -0.65
    KommentareTeilen
    -0.46
    ంత
    -0.45
    класс
    -0.45
    })`
    -0.44
    tagHelperRunner
    -0.44
    цен
    -0.43
     TEND
    -0.42
     et
    -0.41
    Clazz
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.64
     CreateTagHelper
    0.61
     greateſt
    0.57
    cluye
    0.56
     localVar
    0.56
     ſtate
    0.56
     Majefty
    0.56
    csolódó
    0.56
     ſte
    0.55
     المعيارى
    0.54
    Activations Density 2.303%

    No Known Activations