© 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. 8172
    Prev
    Next
    INDEX
    Explanations

    the word "proto" and related programming terms such as "optional", "message", and "unit test".

    oai_token-act-pair · gemini-2.0-flash

    proto

    np_max-act · 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
    +:+
    -0.66
    RunWith
    -0.62
    }{*}{}
    -0.60
    DockStyle
    -0.56
    RTHOOK
    -0.56
    tonode
    -0.54
    AddTagHelper
    -0.52
    ngdoc
    -0.51
    DotNetBar
    -0.50
    forRoot
    -0.48
    POSITIVE LOGITS
    Diwedd
    0.57
    GEBURTSDATUM
    0.54
    minder
    0.49
    phant
    0.48
     Ier
    0.48
    event
    0.47
     ude
    0.47
    kuuta
    0.46
     fossi
    0.46
     Sơ
    0.46
    Activations Density 1.608%

    No Known Activations