© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13589
    Prev
    Next
    INDEX
    Explanations

    United Nations resolutions

    oai_token-act-pair · gemini-2.0-flash

    international organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UN
    -0.73
     UN
    -0.73
    unar
    -0.55
    intern
    -0.54
    UNC
    -0.53
    badlogic
    -0.53
    EDGE
    -0.52
     Himo
    -0.52
    oup
    -0.52
    اة
    -0.51
    POSITIVE LOGITS
    حوالہ
    0.61
     Wikimedijinoj
    0.58
    expandindo
    0.57
    Personensuche
    0.54
     ChromeDriver
    0.50
     remonter
    0.50
    beforeEach
    0.49
    ✨:
    0.49
    Security
    0.49
    )";
    0.48
    Activations Density 0.569%

    No Known Activations