© 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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15340
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gemini-2.0-flash

    thank you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Baillargeon
    -0.73
     intStringLen
    -0.55
     EconPapers
    -0.55
    enumi
    -0.54
     irra
    -0.53
     betweenstory
    -0.52
    Derbyniad
    -0.51
    ▻
    -0.48
     Савез
    -0.48
     Ohne
    -0.47
    POSITIVE LOGITS
     Superhost
    0.64
    ParallelGroup
    0.59
    Välislingid
    0.57
    complexType
    0.53
     szóci
    0.51
    wszy
    0.49
    ENZ
    0.47
    czegó
    0.47
    xler
    0.46
     OnInit
    0.45
    Activations Density 0.854%

    No Known Activations