© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5774
    Prev
    Next
    INDEX
    Explanations

    the word "ended", especially when it concerns a military conflict, political situation or crisis

    oai_token-act-pair · gemini-2.0-flash

    ended

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     ends
    -1.99
     end
    -1.95
     ended
    -1.91
     ending
    -1.82
     Ends
    -1.66
     Ended
    -1.52
    Ending
    -1.47
    Ended
    -1.46
     End
    -1.45
     Ending
    -1.45
    POSITIVE LOGITS
     nakalista
    0.65
     שוליים
    0.56
    WebServlet
    0.53
    UVWXYZ
    0.53
     vuotta
    0.52
    ⎨
    0.52
    kuuta
    0.50
    DoubleQuotes
    0.49
    numerusform
    0.49
    cupertino
    0.48
    Activations Density 2.708%

    No Known Activations