© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12448
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to religion

    oai_token-act-pair · gemini-2.0-flash

    Christianity and religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     CHRISTIAN
    -0.63
     chré
    -0.62
     Christian
    -0.62
    Christian
    -0.58
     /\.
    -0.56
     religieuses
    -0.55
     cristiana
    -0.54
    christian
    -0.54
     Religion
    -0.54
     Religious
    -0.54
    POSITIVE LOGITS
    KeySpec
    0.56
    createStatement
    0.56
     typelib
    0.56
     يتيمه
    0.55
    DllImport
    0.55
    RegressionTest
    0.55
    ModelSerializer
    0.53
    Personendaten
    0.52
     IFTT
    0.52
    tagHelper
    0.52
    Activations Density 7.785%

    No Known Activations