© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9388
    Prev
    Next
    INDEX
    Explanations

    terms related to customer service, business, and insurance

    oai_token-act-pair · gemini-2.0-flash

    customer service

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     createSprite
    -0.54
    Autoritní
    -0.54
     Dir
    -0.52
    enumi
    -0.52
    displayquote
    -0.49
     Extended
    -0.49
    urra
    -0.48
    XmlIgnore
    -0.48
    chige
    -0.47
     Trag
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.70
    AndEndTag
    0.68
     '{@
    0.60
     فريبيس
    0.60
     Chwiliwch
    0.53
    Portale
    0.53
    ніципалі
    0.52
    StoryboardSegue
    0.50
     sạn
    0.50
    TagMode
    0.49
    Activations Density 5.004%

    No Known Activations