© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6524
    Prev
    Next
    INDEX
    Explanations

    the word "constructor" and the string "TODO"

    oai_token-act-pair · gemini-2.0-flash

    constructor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.27
     Houſe
    -1.16
     Majefty
    -1.15
     iconFacebook
    -1.15
     auffi
    -1.05
     itſelf
    -1.02
     houſe
    -1.01
     NDEBUG
    -1.01
    ſelf
    -0.98
     Monfieur
    -0.98
    POSITIVE LOGITS
      
    0.79
    ↵
    0.71
     
    0.69
     '
    0.65
    ReusableCell
    0.57
     "
    0.57
    es
    0.56
    "
    0.54
    i
    0.54
    an
    0.53
    Activations Density 0.976%

    No Known Activations