© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13882
    Prev
    Next
    INDEX
    Explanations

    mentions of hurricanes and their impacts.

    oai_token-act-pair · gemini-2.0-flash

    broad theme, hurricanes/weather.hurricanes/weather

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     CreateTagHelper
    -0.57
    rodow
    -0.57
    terdam
    -0.56
    iaire
    -0.56
    πάρχ
    -0.52
     Alder
    -0.51
    Biografi
    -0.51
     getRule
    -0.50
     ReactDOM
    -0.50
    rungsseite
    -0.50
    POSITIVE LOGITS
    мум
    0.57
    FontOfSize
    0.50
    stateProvider
    0.47
    ssysteme
    0.45
     contextLoads
    0.44
     systé
    0.44
     nudo
    0.44
     Strongly
    0.44
     Fasc
    0.44
     TextInputType
    0.42
    Activations Density 0.814%

    No Known Activations