© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3616
    Prev
    Next
    INDEX
    Explanations

    words related to air pressure, flow and chambers

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "air"

    np_token-act-pair-logits · gpt-4o-mini

    air

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Paglinawan
    -0.79
    UnusedPrivate
    -0.67
    ">//
    -0.67
    tonode
    -0.66
     >=",
    -0.65
     initComponents
    -0.63
     SwitchCompat
    -0.63
     disponibilités
    -0.60
    ]")]
    -0.59
     <",
    -0.59
    POSITIVE LOGITS
     air
    2.45
    air
    1.94
     Air
    1.84
    Air
    1.73
     AIR
    1.68
     aire
    1.45
     lucht
    1.41
    AIR
    1.40
     Luft
    1.33
    空气
    1.26
    Activations Density 2.296%

    No Known Activations