© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8933
    Prev
    Next
    INDEX
    Explanations

    words related to questions, uncertainty, and legal or scientific analysis

    oai_token-act-pair · gemini-2.0-flash

    Determining something

    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
     if
    -2.45
    if
    -2.30
     If
    -1.86
    If
    -1.81
     если
    -1.67
     dacă
    -1.58
     nếu
    -1.54
     jika
    -1.52
     IF
    -1.50
     hvis
    -1.43
    POSITIVE LOGITS
     WEATHER
    0.63
     weather
    0.60
    mybatisplus
    0.59
     lenker
    0.59
     saites
    0.57
    __':
    
    0.56
    __':
    0.55
    tanleria
    0.54
    __":
    
    0.54
    parsedMessage
    0.53
    Activations Density 2.298%

    No Known Activations