© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11341
    Prev
    Next
    INDEX
    Explanations

    non-English names

    oai_token-act-pair · gemini-2.0-flash

    Chinese text/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.77
     surla
    -0.57
    abetes
    -0.57
     Normdatei
    -0.55
    :")
    -0.49
    dónde
    -0.48
    anglès
    -0.48
     fortfarande
    -0.46
    rdı
    -0.46
     Áng
    -0.46
    POSITIVE LOGITS
     Audiodateien
    0.58
    LookAnd
    0.58
    windowFixed
    0.57
    ObjectContext
    0.55
    ISupport
    0.55
     darn
    0.54
    unsplash
    0.54
    pushFollow
    0.54
    sizeCache
    0.53
    ientôt
    0.53
    Activations Density 0.113%

    No Known Activations