© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9385
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is talking about what they have worked on or experienced

    oai_token-act-pair · gemini-2.0-flash

    have

    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
    Negative Logits
    تقاوى
    -0.72
     Appell
    -0.63
     Houſe
    -0.61
     Wikiseite
    -0.59
    titleMargin
    -0.58
     wikipagina
    -0.58
    PyExc
    -0.55
     nào
    -0.54
    GenerationType
    -0.54
    DispatchToProps
    -0.53
    POSITIVE LOGITS
    <bos>
    0.59
    webElement
    0.54
    المشاركات
    0.53
    Gemeinden
    0.52
    يكب
    0.52
     mattino
    0.52
    LogManager
    0.52
     Warga
    0.51
    ParallelGroup
    0.47
    Rcpp
    0.47
    Activations Density 1.108%

    No Known Activations