© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14587
    Prev
    Next
    INDEX
    Explanations

    words containing the letters "ö", "ü", or "Cs"

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ın
    -0.69
    lar
    -0.68
    ArgsConstructor
    -0.63
    ların
    -0.61
    ı
    -0.60
    ları
    -0.59
     da
    -0.59
     mı
    -0.58
    da
    -0.55
    dan
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.83
    vieve
    0.69
    ichier
    0.63
     recherchez
    0.63
     fallu
    0.61
     dévelo
    0.58
    ſelves
    0.58
    ılıyor
    0.57
     Савезне
    0.57
    eleste
    0.57
    Activations Density 0.161%

    No Known Activations