© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to religious belief

    oai_token-act-pair · gemini-2.0-flash

    God, religion

    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
     azi
    -0.56
    QPalette
    -0.55
     صوتيه
    -0.52
    hoeddwyd
    -0.52
    unif
    -0.49
     vapormax
    -0.49
     balan
    -0.49
     Roskov
    -0.48
    StoryboardSegue
    -0.48
    WireFormatLite
    -0.48
    POSITIVE LOGITS
     God
    2.47
    God
    2.19
     god
    1.97
     GOD
    1.85
    god
    1.72
    GOD
    1.66
     Dios
    1.47
     Dieu
    1.39
    Dios
    1.30
     Allah
    1.26
    Activations Density 1.783%

    No Known Activations