© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4680
    Prev
    Next
    INDEX
    Explanations

    LaTeX, HTML, and similar code snippets

    oai_token-act-pair · gemini-2.0-flash

    LaTeX/HTML markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    {
    -0.56
    +:+
    -0.54
     Rest
    -0.54
     |
    -0.54
     j
    -0.53
    •
    -0.53
     jo
    -0.52
     pa
    -0.52
     +
    -0.52
    ■
    -0.50
    POSITIVE LOGITS
     pleaſure
    1.35
     raiſ
    1.29
     ſtate
    1.23
     purpoſe
    1.22
     uſed
    1.20
     tranſ
    1.16
     myſelf
    1.16
     faſt
    1.15
    ſelf
    1.14
    neſs
    1.13
    Activations Density 1.085%

    No Known Activations