© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10561
    Prev
    Next
    INDEX
    Explanations

    lines of code that use the plus sign, curly brackets, and other syntax commonly found in programming

    oai_token-act-pair · gemini-2.0-flash

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    alyptus
    -0.50
    дь
    -0.45
     expert
    -0.44
     dem
    -0.44
     der
    -0.42
     text
    -0.42
    MDL
    -0.41
     med
    -0.39
     the
    -0.39
     sam
    -0.39
    POSITIVE LOGITS
    AndEndTag
    1.00
     EconPapers
    0.91
     <=",
    0.89
    featureID
    0.87
     propOrder
    0.85
     defaultstate
    0.84
     للاسماء
    0.83
     tartalomajánló
    0.82
    تقاوى
    0.82
     kasarigan
    0.81
    Activations Density 9.065%

    No Known Activations