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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15803
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to chemical composition and processes

    oai_token-act-pair · gemini-2.0-flash

    chemical reactions

    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
    NameInMap
    -0.71
    Clik
    -0.57
     tracking
    -0.55
     sml
    -0.54
    Rhestr
    -0.53
     useAppContext
    -0.52
     track
    -0.48
     Track
    -0.47
     AssemblyTitle
    -0.47
    ."],
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.60
     שוליים
    0.57
     relâche
    0.55
     devriez
    0.52
     himo
    0.51
     Masyarakat
    0.50
    ify
    0.49
    sidian
    0.48
    ايا
    0.47
     rowspan
    0.47
    Activations Density 6.574%

    No Known Activations