© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13233
    Prev
    Next
    INDEX
    Explanations

    seemingly unrelated words, possibly capturing multiple topics including Indian festivals, virology, computing terms, and the word "burpee"

    oai_token-act-pair · gemini-2.0-flash

    reference texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Monfieur
    -0.95
     avoient
    -0.90
     auroit
    -0.89
     Theſe
    -0.87
     étoit
    -0.87
     pouvoit
    -0.87
     étoient
    -0.81
     feroit
    -0.80
     enfans
    -0.70
     Inscrivez
    -0.69
    POSITIVE LOGITS
    condido
    0.60
    Synonymes
    0.59
    ArrowToggle
    0.59
    erdings
    0.57
    transQ
    0.56
     comp
    0.56
    AsUp
    0.56
     فهرست
    0.55
    </em>
    0.55
     disambiguazione
    0.54
    Activations Density 1.434%

    No Known Activations