© 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. 15179
    Prev
    Next
    INDEX
    Explanations

    code snippets and XML-like syntax including keywords like "writer", "write", "href", and "ngx"

    oai_token-act-pair · gemini-2.0-flash

    Code involving output/writing

    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
    Xna
    -0.69
     CreateTagHelper
    -0.65
     kyse
    -0.64
    GraphicsUnit
    -0.62
    UnitTesting
    -0.60
     województ
    -0.59
     originais
    -0.57
    Билгалдахарш
    -0.57
    HasForeignKey
    -0.55
     näin
    -0.55
    POSITIVE LOGITS
    ophora
    0.64
    AddHtmlAttribute
    0.56
    nesc
    0.54
     län
    0.54
    buli
    0.54
    퀀
    0.52
    modelBuilder
    0.52
    omitempty
    0.52
     Shanks
    0.52
    ;->
    0.51
    Activations Density 1.935%

    No Known Activations