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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15681
    Prev
    Next
    INDEX
    Explanations

    mentions of carbon, oxygen, and related chemical compounds.

    oai_token-act-pair · gemini-2.0-flash

    carbon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     PhpStorm
    -0.62
    XtraEditors
    -0.59
     ainfi
    -0.58
     initComponents
    -0.57
     Wiktionnaire
    -0.57
     tewas
    -0.56
     quæ
    -0.56
     réussi
    -0.55
    APOLIS
    -0.54
    حوال
    -0.53
    POSITIVE LOGITS
     dy
    0.47
    TestingModule
    0.46
    Portály
    0.46
    oggle
    0.46
     chain
    0.43
     pied
    0.43
     traves
    0.43
    惡
    0.42
     fod
    0.42
    Gweler
    0.42
    Activations Density 0.877%

    No Known Activations