© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5508
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical parts and assemblies with emphasis on physical structure and relation to other objects.

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to mechanical systems

    np_token-act-pair-logits · gpt-4o-mini

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     laufen
    -0.40
     picioare
    -0.40
     actuelles
    -0.40
     femininas
    -0.40
     découver
    -0.39
    arrête
    -0.39
     supérieures
    -0.39
    jen
    -0.39
     kepala
    -0.38
     händer
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.78
     تضيفلها
    0.78
     supplied
    0.77
     placed
    0.75
     connected
    0.70
    HasForeignKey
    0.69
     مواليد
    0.69
     propOrder
    0.69
     attached
    0.68
    CppMethod
    0.68
    Activations Density 2.547%

    No Known Activations