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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 637
    Prev
    Next
    INDEX
    Explanations

    words related to specific events, software development, or sewing/cloth.

    oai_token-act-pair · gemini-2.0-flash

    Religious figures/concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ſeveral
    -0.88
     ſta
    -0.87
     Houſe
    -0.84
     myſelf
    -0.83
     Eſ
    -0.82
     uſed
    -0.82
     raiſ
    -0.81
     houſe
    -0.79
     uſ
    -0.75
     iſt
    -0.75
    POSITIVE LOGITS
     gods
    0.81
     Gods
    0.72
     God
    0.68
     hell
    0.68
     god
    0.66
    gods
    0.65
     Jesus
    0.62
     Hell
    0.61
    god
    0.60
    GOD
    0.59
    Activations Density 3.615%

    No Known Activations