© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6192
    Prev
    Next
    INDEX
    Explanations

    the word "about" in the context of factual information or descriptions

    oai_token-act-pair · gemini-2.0-flash

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     فريبيس
    -0.90
    RegressionTest
    -0.88
    AnimationsModule
    -0.87
    AddTagHelper
    -0.80
    Дереккөздер
    -0.79
    ViewFeatures
    -0.74
    setVerticalGroup
    -0.74
    parsedMessage
    -0.74
    /*
    -0.73
    RenderAtEndOf
    -0.73
    POSITIVE LOGITS
     individuale
    0.66
     líqu
    0.56
     idées
    0.56
     compi
    0.56
     réaction
    0.56
     distinct
    0.54
     Freire
    0.53
     tradis
    0.53
     fær
    0.53
    ciam
    0.53
    Activations Density 0.229%

    No Known Activations