© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15342
    Prev
    Next
    INDEX
    Explanations

    code or syntax for drawing diagrams, particularly using the Forest package in LaTeX.

    oai_token-act-pair · gemini-2.0-flash

    latex code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     незавершена
    -0.65
     dieß
    -0.59
     ſmall
    -0.57
    istia
    -0.53
     Anſ
    -0.53
     CreateTagHelper
    -0.52
    RectangleBorder
    -0.51
     itſelf
    -0.51
     perſon
    -0.50
     Pequ
    -0.50
    POSITIVE LOGITS
    tagHelper
    0.80
     مواليد
    0.66
    OGND
    0.64
    ymce
    0.57
    usas
    0.57
    usa
    0.57
    zuli
    0.55
    PMailer
    0.54
     utan
    0.52
    mead
    0.52
    Activations Density 0.129%

    No Known Activations