© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2012
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in", code, and lists

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     mỗi
    -0.55
     jeder
    -0.55
    complexType
    -0.52
    Chaque
    -0.51
     cada
    -0.50
     each
    -0.50
    ごとに
    -0.50
     każdej
    -0.50
     každé
    -0.50
    tiap
    -0.50
    POSITIVE LOGITS
    ScopeManager
    0.58
    SpringBootTest
    0.56
    __(/*!
    0.52
    íncia
    0.51
     inappropriés
    0.50
    Lähteet
    0.49
    føl
    0.49
     intStringLen
    0.48
     enum
    0.48
    väg
    0.48
    Activations Density 6.229%

    No Known Activations