Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7127
    Prev
    Next
    INDEX
    Explanations

    text relating to rankings, money, and popularity

    oai_token-act-pair · gemini-2.0-flash

    box office and billboard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    
    -0.63
     Мексичка
    -0.62
    ThroughAttribute
    -0.60
     Савезне
    -0.54
     CreateTagHelper
    -0.52
     linkovi
    -0.49
    rament
    -0.48
     nahilalakip
    -0.47
    ฟ้า
    -0.47
    angere
    -0.47
    POSITIVE LOGITS
     propOrder
    0.58
    URLException
    0.57
    ImageContext
    0.55
    yntaxException
    0.54
     ſta
    0.51
    unmodifiable
    0.49
    DockStyle
    0.48
     calculation
    0.48
     calcul
    0.48
    etheless
    0.48
    Activations Density 0.295%

    No Known Activations