© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12212
    Prev
    Next
    INDEX
    Explanations

    technical writing and expressions of difficulty doing something.

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    الدراسه
    -0.81
    awtextra
    -0.62
    argout
    -0.58
    UrlResolution
    -0.55
     ModelRenderer
    -0.54
    Tikang
    -0.52
    ότητα
    -0.51
     StringTokenizer
    -0.51
    hysema
    -0.50
    олові
    -0.50
    POSITIVE LOGITS
     two
    0.97
     three
    0.91
     five
    0.90
     several
    0.88
     four
    0.84
     ten
    0.81
     all
    0.81
     seven
    0.81
     eight
    0.77
     six
    0.76
    Activations Density 3.142%

    No Known Activations