© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10465
    Prev
    Next
    INDEX
    Explanations

    times of day, days of the week, and words "one", "each", and "every"

    oai_token-act-pair · gemini-2.0-flash

    say days of the week/time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    principalTable
    -0.66
     impar
    -0.56
     numerus
    -0.55
    makeText
    -0.53
    oday
    -0.52
     orgasm
    -0.51
     Baillargeon
    -0.49
    EndProject
    -0.48
     virginity
    -0.48
     peper
    -0.47
    POSITIVE LOGITS
    providedIn
    0.52
    routeProvider
    0.51
    ^{-\
    0.46
    awtextra
    0.44
    accio
    0.43
    औ
    0.43
    shortcode
    0.43
    MARCH
    0.43
    nmgp
    0.43
    kuuta
    0.42
    Activations Density 3.260%

    No Known Activations