© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6606
    Prev
    Next
    INDEX
    Explanations

    C/C++ code

    oai_token-act-pair · gemini-2.0-flash

    words with unusual spelling patterns

    np_token-act-pair-logits · gpt-4o-mini

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     g
    -0.77
    ymce
    -0.74
    SharedCtor
    -0.74
     G
    -0.73
     
    -0.73
     van
    -0.72
     Вікіпе
    -0.71
     NSCoder
    -0.69
     T
    -0.69
     As
    -0.69
    POSITIVE LOGITS
     itſelf
    1.36
     myſelf
    1.30
     pleaſure
    1.28
     Monfieur
    1.23
     himſelf
    1.23
     Majefty
    1.20
     themſelves
    1.20
     Reſ
    1.20
     iſt
    1.13
     reaſon
    1.12
    Activations Density 3.673%

    No Known Activations