© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 924
    Prev
    Next
    INDEX
    Explanations

    words relating to death or dying

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -0.76
    ConstraintMaker
    -0.59
    ()].
    -0.58
    MenuInflater
    -0.56
    SpringBootTest
    -0.56
     PropertyChanged
    -0.54
    annica
    -0.54
    MessageTagHelper
    -0.54
    enderror
    -0.52
    jgl
    -0.51
    POSITIVE LOGITS
    toid
    0.57
     nướng
    0.54
    thole
    0.54
    aboo
    0.51
    clearTimeout
    0.50
     girasol
    0.50
     debout
    0.50
     étoile
    0.49
    versy
    0.49
    cimiento
    0.49
    Activations Density 5.165%

    No Known Activations