© 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. 12265
    Prev
    Next
    INDEX
    Explanations

    strings of characters that could be code, especially those containing "\x"

    oai_token-act-pair · 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
    sizeCache
    -0.64
    出版年
    -0.57
    الإنجليزية
    -0.56
    oplan
    -0.52
     EventArgs
    -0.51
    Rptr
    -0.50
    SizeMode
    -0.49
    <bos>
    -0.48
     transférez
    -0.47
     <=",
    -0.47
    POSITIVE LOGITS
     Monfieur
    0.58
    خصة
    0.54
     houſe
    0.49
     onAnimation
    0.48
    awtextra
    0.48
    الحياه
    0.48
     myſelf
    0.48
     الدولى
    0.48
     ſon
    0.48
     itſelf
    0.47
    Activations Density 4.520%

    No Known Activations