© 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. 12100
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related constants

    oai_token-act-pair · gemini-2.0-flash

    clock and proto

    np_max-act · gemini-2.0-flash
    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
     betweenstory
    -0.60
    queryInterface
    -0.57
    pate
    -0.53
    adpleegd
    -0.52
     inoxydable
    -0.50
    alé
    -0.50
    ifflin
    -0.50
    tito
    -0.49
    Karakteristik
    -0.48
    HasBeenSet
    -0.48
    POSITIVE LOGITS
    richTextPanel
    0.59
    rawDesc
    0.57
     Schlä
    0.50
     defaultstate
    0.49
    kháu
    0.48
    cydow
    0.48
     transfieras
    0.47
    хьтан
    0.47
    httphttps
    0.47
     propOrder
    0.46
    Activations Density 1.448%

    No Known Activations