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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 266
    Prev
    Next
    INDEX
    Explanations

    references to authorities, government, political parties, and taking part in celebrations

    oai_token-act-pair · gemini-2.0-flash

    May Day/Labor Day events

    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
     specie
    -0.51
    WebVitals
    -0.49
     betweenstory
    -0.47
     sauve
    -0.45
     élastique
    -0.43
    LabelTagHelper
    -0.41
    carril
    -0.41
     insole
    -0.40
    wood
    -0.40
    wezig
    -0.40
    POSITIVE LOGITS
     BoxDecoration
    0.73
    didSet
    0.68
     يتيمه
    0.67
    __*/
    0.64
     >=",
    0.62
     nahilalakip
    0.61
    wahati
    0.60
    iecie
    0.60
    vereins
    0.59
     propOrder
    0.59
    Activations Density 0.698%

    No Known Activations