© 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. 1181
    Prev
    Next
    INDEX
    Explanations

    a mix of French sentence fragments, words related to IT, and elements of an English application.

    oai_token-act-pair · gemini-2.0-flash

    Article segments

    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
     re
    -2.58
     Re
    -1.89
     res
    -1.86
     Res
    -1.79
    Re
    -1.74
    Res
    -1.59
    re
    -1.39
     RE
    -1.28
     ré
    -1.27
     ре
    -1.26
    POSITIVE LOGITS
    ########.
    0.73
    :✨
    0.65
    évaluateur
    0.60
     culturelles
    0.57
     avoient
    0.57
    ViewImports
    0.57
     juridiques
    0.56
     sauvages
    0.54
     religieuses
    0.54
     rapides
    0.54
    Activations Density 2.080%

    No Known Activations