© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12652
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death, suffering, and remembering people who have passed.

    oai_token-act-pair · gemini-2.0-flash

    died

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     vérit
    -0.61
     varones
    -0.54
     noires
    -0.54
     journalistes
    -0.52
     dangereux
    -0.52
     collègues
    -0.52
     banques
    -0.51
     pères
    -0.51
     tâches
    -0.50
     démocr
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.68
     initComponents
    0.63
     препратки
    0.56
    afficheront
    0.55
     intptr
    0.54
     Roskov
    0.54
    addCriterion
    0.52
     kasarigan
    0.51
    homonymie
    0.50
     Egon
    0.49
    Activations Density 10.095%

    No Known Activations