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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12903
    Prev
    Next
    INDEX
    Explanations

    various bits of code and code-like syntax.

    oai_token-act-pair · gemini-2.0-flash

    <<

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RenderAtEndOf
    -0.70
    GHIJKLM
    -0.53
    ixen
    -0.48
     Paglinawan
    -0.47
     wiser
    -0.47
     peccato
    -0.46
    signol
    -0.45
    ularia
    -0.45
     =======
    -0.44
    hermosa
    -0.44
    POSITIVE LOGITS
    migrationBuilder
    0.72
    modelBuilder
    0.71
     дописавши
    0.64
     kasarigan
    0.63
     cross
    0.60
    AsUp
    0.57
     tắt
    0.56
    ClientSize
    0.54
    TestingModule
    0.54
     '\\;'
    0.53
    Activations Density 4.044%

    No Known Activations