© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2453
    Prev
    Next
    INDEX
    Explanations

    text in French, especially in the context of technical instructions

    oai_token-act-pair · 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
     les
    -0.63
     of
    -0.58
    les
    -0.54
    Les
    -0.54
     Les
    -0.47
    LES
    -0.44
     cest
    -0.43
     ses
    -0.42
     StatefulWidget
    -0.41
     els
    -0.41
    POSITIVE LOGITS
     du
    1.45
     de
    1.05
     d
    1.05
    DockStyle
    0.99
     propOrder
    0.87
    du
    0.85
    BagLayout
    0.80
    存于互联网档案馆
    0.77
    dui
    0.76
     dud
    0.75
    Activations Density 1.100%

    No Known Activations