© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11886
    Prev
    Next
    INDEX
    Explanations

    words related to death

    oai_token-act-pair · gemini-2.0-flash

    died

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     died
    -1.96
     dies
    -1.52
     dying
    -1.27
     Died
    -1.25
    died
    -1.21
    Died
    -1.19
     Dies
    -1.12
     die
    -1.03
     morreu
    -1.02
    Dies
    -0.98
    POSITIVE LOGITS
    DoubleQuotes
    0.68
    UnsafeEnabled
    0.59
     suivantes
    0.58
     AssemblyCulture
    0.56
     astore
    0.54
    UpInside
    0.54
     Soyez
    0.53
     telefónica
    0.52
    manteau
    0.52
    Pratique
    0.52
    Activations Density 0.754%

    No Known Activations