© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12660
    Prev
    Next
    INDEX
    Explanations

    words that end in "ic", "tion", "al", "ize", or that are capitalized acronyms or names, suggesting it identifies terminology

    oai_token-act-pair · gemini-2.0-flash

    technical writing/legal documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.86
     kaarangay
    -0.86
     Meksiku
    -0.84
     betweenstory
    -0.83
    writeFieldEnd
    -0.82
     otomatig
    -0.81
    KommentareTeilen
    -0.80
     utafitiHapana
    -0.80
     виправивши
    -0.79
     noDo
    -0.78
    POSITIVE LOGITS
     H
    0.52
     T
    0.47
     are
    0.47
     a
    0.46
     B
    0.45
     X
    0.44
     to
    0.43
     Sig
    0.42
    uh
    0.42
     He
    0.42
    Activations Density 26.823%

    No Known Activations