© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5307
    Prev
    Next
    INDEX
    Explanations

    words related to material science and manufacturing processes, specifically those involving semiconductors, metals, and adhesives

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming concepts

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

    Microscopic structure formation

    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
    alisa
    -0.52
     lenker
    -0.52
    IDA
    -0.48
     informasjon
    -0.47
    IDAS
    -0.46
    aliana
    -0.46
     _$
    -0.45
     póster
    -0.45
    ümü
    -0.45
    ida
    -0.44
    POSITIVE LOGITS
    InjectAttribute
    0.77
     سكانية
    0.72
    elemField
    0.70
    MemoryWarning
    0.67
    UnitTesting
    0.62
    SBATCH
    0.61
    onoi
    0.59
    TestingModule
    0.59
    MockBean
    0.56
     <>",
    0.56
    Activations Density 11.216%

    No Known Activations