© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4560
    Prev
    Next
    INDEX
    Explanations

    a combination of words from different languages, different topics like medicine, politics or programming and also sentence delimiters and question marks

    oai_token-act-pair · gemini-2.0-flash

    tokens related to yogurt consumption

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     sanitaires
    -0.80
    脚注の使い方
    -0.80
    Clik
    -0.77
    بوابة
    -0.76
     AppColors
    -0.75
    Hochspringen
    -0.75
     الحره
    -0.73
    Personendaten
    -0.72
    الحياه
    -0.72
    لينكات
    -0.72
    POSITIVE LOGITS
     zda
    0.35
     gọn
    0.35
     на
    0.33
     lands
    0.33
     tez
    0.33
    getItemId
    0.32
    currentColor
    0.32
     gema
    0.31
     Szcz
    0.30
    Factories
    0.30
    Activations Density 2.776%

    No Known Activations