© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8241
    Prev
    Next
    INDEX
    Explanations

    words and phrases like "this will" and "that way" that connect parts of an argument or explanation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    这样
    -0.46
     Mercantile
    -0.42
     Cym
    -0.41
     BART
    -0.41
     Orrell
    -0.40
     sinn
    -0.40
    源
    -0.39
    関
    -0.39
    #
    -0.39
    stand
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.76
    StoryboardSegue
    0.75
     للاسماء
    0.71
     الحره
    0.68
    NameInMap
    0.68
    Fordítás
    0.67
    raszam
    0.66
    Παραπομπές
    0.66
    :][
    0.63
    Спасылкі
    0.63
    Activations Density 1.328%

    No Known Activations