© 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. 4988
    Prev
    Next
    INDEX
    Explanations

    a combination of scientific terms, seemingly random capitalized words, and medical terminology.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    WriteTagHelper
    -0.91
    ஦
    -0.90
    <unused99>
    -0.89
    <unused3>
    -0.89
    <unused47>
    -0.89
    <unused21>
    -0.89
    <unused41>
    -0.89
    <unused38>
    -0.89
    <unused6>
    -0.89
    <unused14>
    -0.89
    POSITIVE LOGITS
    rungsseite
    0.13
     démocr
    0.12
     flesta
    0.07
     líqu
    0.04
     clínicas
    0.02
     jurí
    0.01
     définiti
    0.01
     boî
    0.00
     judiciales
    0.00
     civiles
    -0.00
    Activations Density 52.528%

    No Known Activations