© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7504
    Prev
    Next
    INDEX
    Explanations

    terms related to religion, mainly Christianity/Islam

    oai_token-act-pair · gemini-2.0-flash

    Words ending in ism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     airbag
    -0.51
     StringTokenizer
    -0.47
     Warehouse
    -0.45
     forklift
    -0.45
     compressor
    -0.44
     Deere
    -0.44
     airbags
    -0.43
     CarPlay
    -0.43
     warehouse
    -0.43
     blender
    -0.43
    POSITIVE LOGITS
    osoever
    0.47
     Psal
    0.47
     Gentiles
    0.46
     Prophets
    0.44
     Religion
    0.43
     Prophecy
    0.42
     Pythagoras
    0.42
     Philosop
    0.41
    ticism
    0.40
    itarianism
    0.40
    Activations Density 46.685%

    No Known Activations