© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7175
    Prev
    Next
    INDEX
    Explanations

    descriptions of workouts

    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
    Negative Logits
    twimg
    -0.49
     alér
    -0.45
    Consts
    -0.43
    ozof
    -0.42
     Unsc
    -0.42
    Obrázky
    -0.40
    ก่
    -0.40
     drogas
    -0.40
     Ehe
    -0.40
    mars
    -0.40
    POSITIVE LOGITS
    Geplaatst
    1.15
    GEBURTSDATUM
    0.95
    تقاوى
    0.89
     nakalista
    0.79
     الاطلاع
    0.73
     محفوظة
    0.71
    addGap
    0.70
    GraphicsUnit
    0.69
     ویکی‌پدی
    0.68
     ویکی‌پدیای
    0.68
    Activations Density 13.765%

    No Known Activations