© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4651
    Prev
    Next
    INDEX
    Explanations

    agency names, followed by the word "has" and other function words like "also", "is", or "a"

    oai_token-act-pair · gemini-2.0-flash

    has

    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
    Has
    -0.66
     disponibilités
    -0.57
     Has
    -0.56
    Was
    -0.48
     Was
    -0.47
    has
    -0.47
     Had
    -0.45
    iecie
    -0.44
    Have
    -0.44
    Had
    -0.43
    POSITIVE LOGITS
    ^(@)
    0.71
     conferred
    0.71
    adpleegd
    0.66
     spelled
    0.65
     demonstrated
    0.65
     pointed
    0.64
     photolibrary
    0.64
     displayed
    0.64
    CloseOperation
    0.63
    lained
    0.63
    Activations Density 2.205%

    No Known Activations