© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15531
    Prev
    Next
    INDEX
    Explanations

    words related to medicine, politics, government, economics, and time measurement

    oai_token-act-pair · gemini-2.0-flash

    reference text

    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
     Houſe
    -0.90
     purpoſe
    -0.90
     Chriftian
    -0.85
     pleaſure
    -0.85
     myſelf
    -0.85
     itſelf
    -0.85
     Shakspeare
    -0.84
     Reſ
    -0.84
    ſelves
    -0.84
     reaſon
    -0.83
    POSITIVE LOGITS
    ,
    2.08
     ,
    0.70
     And
    0.59
    (),
    0.50
    And
    0.44
    、
    0.44
     же
    0.42
     Vikipedi
    0.41
     as
    0.41
    .,
    0.38
    Activations Density 9.277%

    No Known Activations