© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14563
    Prev
    Next
    INDEX
    Explanations

    words associated with manufacturing and standardization

    oai_token-act-pair · gemini-2.0-flash

    factory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     <=",
    -1.21
    WriteBarrier
    -1.04
    addGap
    -0.92
    setVerticalGroup
    -0.87
     مشين
    -0.84
    الإنجليزية
    -0.83
    UnsafeEnabled
    -0.83
    ership
    -0.83
    Diwedd
    -0.81
    ValueStyle
    -0.77
    POSITIVE LOGITS
    ্
    0.46
     whor
    0.44
     really
    0.41
    really
    0.40
    ed
    0.40
     procedure
    0.40
    an
    0.39
    per
    0.39
     contu
    0.38
    2
    0.38
    Activations Density 0.468%

    No Known Activations