© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14290
    Prev
    Next
    INDEX
    Explanations

    the word "quite" and words appearing nearby

    oai_token-act-pair · gemini-2.0-flash

    quite

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     quite
    -1.04
     Quite
    -0.96
    quite
    -0.95
    Quite
    -0.93
     pretty
    -0.79
    Pretty
    -0.74
    pretty
    -0.72
     Pretty
    -0.65
    Much
    -0.63
     bastante
    -0.60
    POSITIVE LOGITS
     للمعارف
    0.60
    WillAppear
    0.59
    новниш
    0.58
    saraba
    0.57
     pinulongan
    0.57
     UNIVE
    0.56
    enetrable
    0.56
    setLayoutManager
    0.56
    UFACT
    0.54
     古着
    0.52
    Activations Density 4.870%

    No Known Activations