© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5640
    Prev
    Next
    INDEX
    Explanations

    references to religion and authority

    oai_token-act-pair · gemini-2.0-flash

    Religion/Bible

    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
     suggesting
    -0.73
     suggestion
    -0.63
    Portail
    -0.61
     indicating
    -0.60
     indicando
    -0.60
    Discus
    -0.57
    DockStyle
    -0.56
     describing
    -0.55
     Suggest
    -0.55
     suggests
    -0.55
    POSITIVE LOGITS
    \}_{
    0.70
    UVWXYZ
    0.65
    Rhestr
    0.59
     kaarangay
    0.58
     Wikimedijinoj
    0.57
     Exactos
    0.57
    httphttps
    0.56
    \{\\
    0.55
    __))
    0.54
     Réponses
    0.53
    Activations Density 8.377%

    No Known Activations