© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14985
    Prev
    Next
    INDEX
    Explanations

    code snippets using parentheses, equals signs, and the word "List"

    oai_token-act-pair · gemini-2.0-flash

    =

    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
    :✨
    -0.67
     متعلقه
    -0.63
     $_"
    -0.63
    ſelves
    -0.60
    ſelf
    -0.60
     *++
    -0.59
    dings
    -0.56
     venons
    -0.55
     Мексичка
    -0.54
     gawas
    -0.54
    POSITIVE LOGITS
     (
    0.58
    GOTREF
    0.57
    nonatomic
    0.53
    __((
    0.53
    invokeLater
    0.51
    WithIdentifier
    0.51
     ((
    0.50
    MemoryWarning
    0.49
    (
    0.48
    ((
    0.47
    Activations Density 0.459%

    No Known Activations