© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10870
    Prev
    Next
    INDEX
    Explanations

    the words "world" and "estate"

    oai_token-act-pair · gemini-2.0-flash

    real estate and world

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <strong>
    -0.59
    <sup>
    -0.57
    !
    -0.56
    ,
    -0.55
     kond
    -0.54
    k
    -0.50
    .
    -0.50
    <b>
    -0.49
     trop
    -0.49
    [
    -0.49
    POSITIVE LOGITS
     Италијани
    1.09
     pouvoit
    0.99
     feroit
    0.98
     Monfieur
    0.97
    ']))
    0.97
     auroit
    0.97
     propOrder
    0.97
     étoient
    0.97
     étoit
    0.95
     InputDecoration
    0.95
    Activations Density 0.186%

    No Known Activations