© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4199
    Prev
    Next
    INDEX
    Explanations

    words related to materials processing and fabrication techniques, particularly in semiconductor manufacturing.

    oai_token-act-pair · gemini-2.0-flash

    terminology related to processes and methods in manufacturing

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

    manufacturing and processing

    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
    تقاوى
    -0.94
    Datuak
    -0.93
    ⓧ
    -0.86
     }}"></
    -0.85
     disambiguazione
    -0.84
    TagHelper
    -0.81
     unknownFields
    -0.79
    脚注の使い方
    -0.76
    rungsseite
    -0.75
    }}/>
    -0.75
    POSITIVE LOGITS
     cycle
    0.52
     activities
    0.51
    stech
    0.48
     method
    0.48
     equipment
    0.46
     procedure
    0.46
     Procedure
    0.46
     Plan
    0.45
     plan
    0.45
     protocol
    0.45
    Activations Density 2.581%

    No Known Activations