© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15134
    Prev
    Next
    INDEX
    Explanations

    a variety of specific characters in code, legal documents, and html

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Paglinawan
    -1.46
     nakalista
    -1.45
    RenderAtEndOf
    -1.34
     تضيفلها
    -1.31
     GenerationType
    -1.26
     AspNetCore
    -1.20
     CreateTagHelper
    -1.20
    Geplaatst
    -1.20
    WithIOException
    -1.19
     ویکی‌پدی
    -1.18
    POSITIVE LOGITS
    ↵
    0.70
     
    0.62
     A
    0.56
      
    0.52
    ↵↵
    0.51
    <b>
    0.47
     T
    0.47
     R
    0.45
     O
    0.44
    ↵↵↵
    0.43
    Activations Density 0.570%

    No Known Activations