© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13612
    Prev
    Next
    INDEX
    Explanations

    mostly or many of something in particular

    oai_token-act-pair · gemini-2.0-flash

    sets and categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WebServlet
    -0.64
     EconPapers
    -0.63
     handleMessage
    -0.59
     onAnimation
    -0.56
    :+:
    -0.55
    getline
    -0.52
    simov
    -0.52
    insics
    -0.52
    <?
    -0.52
     cherchés
    -0.50
    POSITIVE LOGITS
    ValueGenerated
    0.58
     {}'.
    0.54
    httphttps
    0.51
    INCREF
    0.50
    nje
    0.48
    })();
    0.47
    Brainz
    0.46
    StackNavigator
    0.46
     brig
    0.45
    yszcz
    0.44
    Activations Density 4.178%

    No Known Activations