© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    words that end in "ing", "ecti", "tial", or "ogi", and also the word "gauge"

    oai_token-act-pair · gemini-2.0-flash

    gauge

    np_max-act · gemini-2.0-flash

    say "space"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     članak
    -0.62
    SuppressLint
    -0.57
     חיצוניים
    -0.55
     Перейти
    -0.54
     vägen
    -0.54
     تعدى
    -0.53
    Hochspringen
    -0.52
    
    -0.52
     parça
    -0.52
      (
    -0.50
    POSITIVE LOGITS
    RTLR
    0.55
    sizeCache
    0.51
    LETIN
    0.51
    Parameteri
    0.49
     Ue
    0.48
    PostInfinity
    0.48
    SharedDtor
    0.47
    PreExecute
    0.47
    forRoot
    0.46
     dAtA
    0.45
    Activations Density 0.784%

    No Known Activations