© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7338
    Prev
    Next
    INDEX
    Explanations

    describes religious services such as mass or communion

    oai_token-act-pair · gemini-2.0-flash

    prayer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    aarrggbb
    -0.71
    MemoryWarning
    -0.52
     calldata
    -0.50
     Wass
    -0.50
    Wass
    -0.49
    ανε
    -0.49
     encar
    -0.47
    zessin
    -0.47
    osomal
    -0.46
    ΙΣ
    -0.46
    POSITIVE LOGITS
     prayer
    0.98
     Prayer
    0.91
     devotional
    0.86
    prayer
    0.85
     pray
    0.85
     praying
    0.83
    Prayer
    0.83
     prayed
    0.82
     worship
    0.82
     spirituality
    0.81
    Activations Density 0.798%

    No Known Activations