© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8472
    Prev
    Next
    INDEX
    Explanations

    mentions of the Christian God or concepts involving discovering God's greatness.

    oai_token-act-pair · gemini-2.0-flash

    references to divinity or God

    np_token-act-pair-logits · gpt-4o-mini

    He/Him pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    MLLoader
    -0.51
    MarshalTo
    -0.50
     Telex
    -0.48
    Бележки
    -0.48
     Overland
    -0.47
    afficheront
    -0.47
     خارجية
    -0.46
     Equitable
    -0.44
     الرياضيه
    -0.44
    Viitteet
    -0.43
    POSITIVE LOGITS
     His
    1.70
    His
    1.38
     He
    1.37
     Himself
    1.31
     Him
    1.29
     Он
    1.21
     Его
    1.15
    Him
    1.00
    He
    0.98
     Your
    0.93
    Activations Density 5.851%

    No Known Activations