© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4647
    Prev
    Next
    INDEX
    Explanations

    words and especially phrases related to oxygen, saturation, atmosphere, and transport

    oai_token-act-pair · gemini-2.0-flash

    oxygen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     recruiters
    -0.55
     recruiter
    -0.53
     chasse
    -0.52
    WhereInput
    -0.50
     executive
    -0.48
    windowFixed
    -0.46
    بد
    -0.46
    hassee
    -0.45
    ânsito
    -0.44
    buttonBar
    -0.44
    POSITIVE LOGITS
     oxygen
    1.19
     Oxygen
    1.02
    Oxygen
    0.91
    oxygen
    0.90
    xygen
    0.88
     oxigen
    0.82
    氧
    0.79
     oxígeno
    0.73
    XYGEN
    0.72
     ox
    0.69
    Activations Density 0.842%

    No Known Activations