© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9601
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    tau

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     linkovi
    -0.74
    ymce
    -0.69
    <bos>
    -0.64
    TestBed
    -0.54
    Życiorys
    -0.53
     eens
    -0.53
    jiga
    -0.53
    Mutagenicity
    -0.49
    PropertyChanged
    -0.49
     fotografico
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.75
    makeConstraints
    0.65
    tagext
    0.64
     ✭✭
    0.63
     ویکی‌پدی
    0.60
    ">',
    0.60
    posedge
    0.60
     препратки
    0.60
    ρης
    0.59
    "],
    0.58
    Activations Density 3.188%

    No Known Activations