© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1852
    Prev
    Next
    INDEX
    Explanations

    mentions of Catholicism or Catholic organizations

    oai_token-act-pair · gemini-2.0-flash

    terms related to religious life or community

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

    Catholicism

    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
     pop
    -0.77
     Pop
    -0.65
    ppins
    -0.65
    Pap
    -0.63
    Pop
    -0.63
    pap
    -0.62
     pap
    -0.61
    PerformLayout
    -0.60
     papa
    -0.59
     pops
    -0.58
    POSITIVE LOGITS
     Meksiku
    0.58
     NSCoder
    0.52
     esternos
    0.52
    GLFW
    0.51
     ministerial
    0.45
     pro
    0.44
    TypedDataSet
    0.44
     Ministerial
    0.43
     Tab
    0.43
     formation
    0.43
    Activations Density 1.233%

    No Known Activations