© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13460
    Prev
    Next
    INDEX
    Explanations

    words and phrases used to describe buying products from a vendor

    oai_token-act-pair · gemini-2.0-flash

    IT and software application terminology

    np_token-act-pair-logits · gpt-4o-mini

    IT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     كومونز
    -0.73
    ſelf
    -0.72
     againſt
    -0.69
     تضيفلها
    -0.68
     Houſe
    -0.67
     myſelf
    -0.66
    expandindo
    -0.66
     티즈
    -0.62
     itſelf
    -0.62
     Majefty
    -0.61
    POSITIVE LOGITS
     IT
    0.82
    IT
    0.68
    Portale
    0.55
    enterOuterAlt
    0.53
     ERP
    0.49
     helst
    0.48
    rec
    0.47
    Core
    0.46
     back
    0.46
    Info
    0.46
    Activations Density 2.251%

    No Known Activations