© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10849
    Prev
    Next
    INDEX
    Explanations

    text related to God, religion, and spirituality

    oai_token-act-pair · gemini-2.0-flash

    death, passed loved ones

    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
     CreateTagHelper
    -1.03
     Monfieur
    -0.84
     itſelf
    -0.84
     Efq
    -0.81
     iſt
    -0.81
    WebServlet
    -0.78
     OFDb
    -0.77
     myſelf
    -0.74
    setVerticalGroup
    -0.74
     leſs
    -0.73
    POSITIVE LOGITS
    mişti
    0.51
     home
    0.51
     M
    0.49
    diğini
    0.46
    diğim
    0.45
    diğinde
    0.43
     Home
    0.43
     U
    0.42
     P
    0.42
    melidir
    0.40
    Activations Density 0.640%

    No Known Activations