© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7474
    Prev
    Next
    INDEX
    Explanations

    javascript code structures, especially testing-related keywords and function definitions

    oai_token-act-pair · gemini-2.0-flash

    say "it"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Gön
    -0.63
     betweenstory
    -0.61
     Lati
    -0.60
     paraf
    -0.60
     TextAppearance
    -0.59
    PreferredItem
    -0.58
    省市镇
    -0.58
    iecie
    -0.57
     AspNetCore
    -0.57
    +#+
    -0.57
    POSITIVE LOGITS
     picioare
    0.54
    seamnă
    0.54
     čierna
    0.50
    beforeAll
    0.50
     pareti
    0.50
     pelúcia
    0.48
     gambe
    0.48
     portátiles
    0.46
     maș
    0.46
     jälkeen
    0.46
    Activations Density 13.545%

    No Known Activations