© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14657
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Pat." or the word "pat" in lowercase followed by other letters

    oai_token-act-pair · gemini-2.0-flash

    Pat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SequentialGroup
    -0.60
    わけ
    -0.51
     cu
    -0.50
     cup
    -0.49
    WriteString
    -0.48
    ден
    -0.48
    govina
    -0.48
     Gru
    -0.47
    canada
    -0.47
     бук
    -0.46
    POSITIVE LOGITS
    ArgsConstructor
    0.70
     createState
    0.66
    ArrowToggle
    0.66
    AndEndTag
    0.63
     للاسماء
    0.60
    Personensuche
    0.59
    ellido
    0.58
     jScrollPane
    0.57
    Manbalar
    0.56
     @"/
    0.56
    Activations Density 0.571%

    No Known Activations