© 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. 9596
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical notation and jargon.

    oai_token-act-pair · gemini-2.0-flash

    0 and cm

    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
     &___
    -0.76
     виправивши
    -0.67
     noDo
    -0.64
    ГЛА
    -0.62
    Jeografia
    -0.61
    itettura
    -0.59
    /*---
    -0.58
     transfieras
    -0.57
    цездатний
    -0.55
    Література
    -0.54
    POSITIVE LOGITS
    ParallelGroup
    0.66
    ApiModel
    0.62
     الاطلاع
    0.58
    bagai
    0.56
    новништво
    0.55
    ioutil
    0.55
    tagHelper
    0.54
    Архівовано
    0.52
    preventDefault
    0.52
    页面存档备份
    0.51
    Activations Density 1.778%

    No Known Activations