© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13899
    Prev
    Next
    INDEX
    Explanations

    content related to the Islamic prophet Muhammad and his teachings.

    oai_token-act-pair · gemini-2.0-flash

    words related to religious texts or revelations

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

    religious revelation

    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
    WebVitals
    -0.68
    PreferredItem
    -0.61
     فريبيس
    -0.60
    ScopeManager
    -0.60
     onOptions
    -0.59
    RenderAtEndOf
    -0.57
    TagMode
    -0.56
     Riproduzione
    -0.56
    atguigu
    -0.54
     adopté
    -0.54
    POSITIVE LOGITS
     revelation
    0.62
    prop
    0.62
    Reve
    0.59
     revealed
    0.59
    revel
    0.57
     Holy
    0.57
     script
    0.53
     revelations
    0.53
     Bible
    0.52
    revealed
    0.52
    Activations Density 1.772%

    No Known Activations