© 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. 4802
    Prev
    Next
    INDEX
    Explanations

    XML tags with the word "Reponse" (response in French)

    oai_token-act-pair · gemini-2.0-flash

    technical and scientific contexts

    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
     Seligman
    -0.49
     Anand
    -0.47
    OutputPath
    -0.47
     rédaction
    -0.46
     Alfons
    -0.46
    bein
    -0.44
     Northam
    -0.44
     Dian
    -0.44
    ignor
    -0.44
     Marian
    -0.43
    POSITIVE LOGITS
    chtete
    0.66
     Dine
    0.63
    dide
    0.59
    rike
    0.59
    CAPE
    0.59
     Vise
    0.58
     Gode
    0.58
    gale
    0.57
    BITE
    0.57
     Mache
    0.57
    Activations Density 4.590%

    No Known Activations