© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13182
    Prev
    Next
    INDEX
    Explanations

    words associated with the Jehovah's Witnesses and Mormon temples.

    oai_token-act-pair · gemini-2.0-flash

    Religious discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Dalai
    -0.53
     Bane
    -0.51
     Commune
    -0.50
    Activités
    -0.48
    سياسي
    -0.48
     prefent
    -0.44
     Kommune
    -0.44
     Banerjee
    -0.44
     Hift
    -0.43
     xoay
    -0.43
    POSITIVE LOGITS
    Notae
    0.61
     تضيفلها
    0.60
    SpringBootTest
    0.58
    klart
    0.57
    Personensuche
    0.56
    awtextra
    0.54
    onView
    0.53
    audi
    0.53
    wts
    0.53
    ształ
    0.52
    Activations Density 0.695%

    No Known Activations