© 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. 9821
    Prev
    Next
    INDEX
    Explanations

    a variety of nouns in different languages and contexts.

    oai_token-act-pair · gemini-2.0-flash

    Brief

    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
    </em>
    -0.36
    city
    -0.36
    Former
    -0.36
    y
    -0.35
    ↵
    -0.34
     stay
    -0.34
    対
    -0.34
    ↵↵
    -0.33
    outer
    -0.33
    нева
    -0.33
    POSITIVE LOGITS
    <bos>
    1.57
    AddTagHelper
    1.09
    Diwedd
    1.02
    Vidite
    1.01
     kasarigan
    0.91
    awtextra
    0.91
    expandindo
    0.89
    ьаж
    0.88
     defaultstate
    0.86
    InitVars
    0.84
    Activations Density 20.360%

    No Known Activations