© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13114
    Prev
    Next
    INDEX
    Explanations

    hyphenated words, ellipses, and sentence fragments in legal or medical text

    oai_token-act-pair · gemini-2.0-flash

    ellipses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     HSS
    -0.65
     itſelf
    -0.63
    ſelves
    -0.63
     GSP
    -0.63
     Carls
    -0.62
    UnusedPrivate
    -0.61
     مرئيه
    -0.61
     ſche
    -0.60
     ſtate
    -0.60
     jsPsych
    -0.60
    POSITIVE LOGITS
      
    0.68
    ratulations
    0.66
    nourriture
    0.66
    experiments
    0.65
    redient
    0.64
    ropriate
    0.64
     gyakor
    0.62
    ecutive
    0.62
    ecution
    0.60
    wnież
    0.60
    Activations Density 3.242%

    No Known Activations