© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8070
    Prev
    Next
    INDEX
    Explanations

    emoticons, especially the smiley face, and some diacritic characters likely from European languages

    oai_token-act-pair · gemini-2.0-flash

    :)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -1.02
    <eos>
    -0.93
    <bos>
    -0.81
     
    -0.73
     in
    -0.70
    ↵
    -0.69
    ’
    -0.66
     z
    -0.65
     just
    -0.62
    '
    -0.60
    POSITIVE LOGITS
    
    1.61
    parsedMessage
    1.46
    tvguidetime
    1.38
     CreateTagHelper
    1.35
     مشين
    1.34
     متعلقه
    1.28
    存于互联网档案馆
    1.28
     MainAxisSize
    1.27
     Мексичка
    1.27
     للاسماء
    1.25
    Activations Density 1.117%

    No Known Activations