© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1941
    Prev
    Next
    INDEX
    Explanations

    chemical formulas, especially those containing oxygen, nitrogen, carbon dioxide, or halogens

    oai_token-act-pair · gemini-2.0-flash

    oxygen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     said
    -0.49
     r
    -0.46
     \
    -0.45
    最快更新
    -0.45
    APON
    -0.45
     k
    -0.45
    benzyl
    -0.44
    nimmt
    -0.43
     h
    -0.43
    ↵↵↵
    -0.42
    POSITIVE LOGITS
     Nitrogen
    0.77
     nitrogen
    0.72
    Nitrogen
    0.72
    nitrogen
    0.70
     OCR
    0.67
     Oxygen
    0.67
    IRUS
    0.67
     oprot
    0.65
    Oxygen
    0.65
     nahilalakip
    0.65
    Activations Density 1.208%

    No Known Activations