© 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. 1420
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and chemical composition, especially those concerning arid environments and minerals.

    oai_token-act-pair · gemini-2.0-flash

    salt/salinity

    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
     salt
    -1.14
     Salt
    -1.13
    Salt
    -1.09
    salt
    -0.94
    __":
    -0.91
     SALT
    -0.86
    IndentedString
    -0.79
    GEBURTSDATUM
    -0.78
    GOTREF
    -0.74
    PyExc
    -0.74
    POSITIVE LOGITS
     sal
    0.91
     للمعارف
    0.73
     Grosso
    0.56
    pick
    0.56
     pick
    0.51
     Sal
    0.50
    LogManager
    0.49
    Pick
    0.48
     chlor
    0.48
    sal
    0.47
    Activations Density 4.612%

    No Known Activations