© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14514
    Prev
    Next
    INDEX
    Explanations

    varied set of words relating to greeting, acknowledging, or being nice to people, sometimes including foreign languages

    oai_token-act-pair · gemini-2.0-flash

    hospitality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ритори
    -0.59
    וך
    -0.57
    setArguments
    -0.53
     giusti
    -0.52
    CellStyle
    -0.51
     Isles
    -0.50
    huy
    -0.50
     romantique
    -0.50
     Datenbank
    -0.49
     pilihan
    -0.49
    POSITIVE LOGITS
     welcome
    1.37
     welcoming
    1.25
    Welcome
    1.23
     WELCOME
    1.19
     Welcome
    1.16
     welcomes
    1.13
    WELCOME
    1.10
    welcome
    1.10
     welcomed
    1.06
     bienvenida
    0.96
    Activations Density 0.744%

    No Known Activations