© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12787
    Prev
    Next
    INDEX
    Explanations

    words associated with formal government, finance, and construction projects.

    oai_token-act-pair · gemini-2.0-flash

    government/official matters

    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
     MotionEvent
    -0.59
     BorderRadius
    -0.57
    AndEndTag
    -0.57
    IMPORTED
    -0.54
    UPAC
    -0.53
    querque
    -0.53
     GlobalKey
    -0.51
    +:+
    -0.49
     SCHEME
    -0.49
    abestanden
    -0.49
    POSITIVE LOGITS
    <bos>
    0.91
     myſelf
    0.55
    intahan
    0.54
     ویکی‌پدیا
    0.52
    setVerticalGroup
    0.50
    ⓧ
    0.50
     extérieur
    0.48
    Geplaatst
    0.48
     themſelves
    0.48
     itſelf
    0.47
    Activations Density 1.678%

    No Known Activations