© 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. 9322
    Prev
    Next
    INDEX
    Explanations

    a variety of phrases in different languages related to computing and/or the internet

    oai_token-act-pair · gemini-2.0-flash

    computer code and errors

    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
     jambes
    -0.86
     oreilles
    -0.86
     cœurs
    -0.85
     rêves
    -0.85
     egna
    -0.83
     nuages
    -0.82
     dieux
    -0.82
     mères
    -0.82
     âmes
    -0.81
     récompenses
    -0.81
    POSITIVE LOGITS
     purpoſe
    1.00
     pleaſure
    0.94
     Monfieur
    0.90
    ſelf
    0.88
     raiſ
    0.87
     Diſ
    0.87
     houſe
    0.85
    ſelves
    0.85
     cauſe
    0.84
     ſta
    0.84
    Activations Density 0.366%

    No Known Activations