© 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. 9599
    Prev
    Next
    INDEX
    Explanations

    code excerpts related to natural language processing and some part-of-speech tags and related terms

    oai_token-act-pair · gemini-2.0-flash

    ner

    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
    ("/:
    -0.51
    ('/:
    -0.50
    EMU
    -0.50
    delwed
    -0.50
     Republi
    -0.50
    LookAnd
    -0.50
    équ
    -0.49
     Faul
    -0.49
    TestingModule
    -0.48
    FieldBuilder
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.93
    يكب
    0.75
    webElementXpaths
    0.69
    -------------</
    0.67
     HttpNotFound
    0.59
     otomatig
    0.59
    ьаж
    0.57
     Normdatei
    0.56
    ванович
    0.54
    genstein
    0.54
    Activations Density 2.258%

    No Known Activations