© 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. 16274
    Prev
    Next
    INDEX
    Explanations

    mentions of injuries or fatalities in the context of protests.

    oai_token-act-pair · gemini-2.0-flash

    Deaths and injuries

    np_max-act-logits · 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
    ########.
    -0.83
     saites
    -0.82
    发表于
    -0.81
    rrggbb
    -0.79
    AsUp
    -0.79
     Италијани
    -0.77
    enderror
    -0.76
    enumi
    -0.75
     EconPapers
    -0.73
     nakalista
    -0.70
    POSITIVE LOGITS
    boutin
    0.43
    ri
    0.38
     che
    0.37
     por
    0.36
    porte
    0.35
    ổng
    0.35
     kir
    0.35
    证
    0.34
    ствует
    0.34
     law
    0.34
    Activations Density 2.088%

    No Known Activations