© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12555
    Prev
    Next
    INDEX
    Explanations

    words or characters appearing in computing contexts, like "L1 cache", but also the word "slide"

    oai_token-act-pair · gemini-2.0-flash

    slide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     slide
    -1.13
     slides
    -0.96
     Slide
    -0.96
    Slide
    -0.94
    slide
    -0.94
     sliding
    -0.88
     slipping
    -0.88
     glisser
    -0.88
     slip
    -0.87
    slip
    -0.84
    POSITIVE LOGITS
     kasarigan
    0.77
    ViewFeatures
    0.70
    BeginInit
    0.68
     createState
    0.61
     Anſ
    0.59
    featureID
    0.58
    PerformLayout
    0.58
    CodedInputStream
    0.57
     batteries
    0.57
    ajemy
    0.56
    Activations Density 2.090%

    No Known Activations