© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12465
    Prev
    Next
    INDEX
    Explanations

    LaTeX code, especially expressions with exponents

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    المشاركات
    -0.51
     مُعرِّف
    -0.51
     रा
    -0.45
     Теперь
    -0.45
     summer
    -0.44
     now
    -0.44
    ]-->
    -0.44
    Slf
    -0.44
    PERT
    -0.43
     Llu
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.75
     mergeFrom
    0.66
     GenerationType
    0.65
    erunner
    0.64
     Paglinawan
    0.63
    windowFixed
    0.60
     AssemblyProduct
    0.60
    AnimationsModule
    0.58
    cuadro
    0.58
    SqlDataReader
    0.58
    Activations Density 1.783%

    No Known Activations