© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4875
    Prev
    Next
    INDEX
    Explanations

    the word "urgency" or phrases about things needing to happen quickly

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     rush
    -1.91
     rapid
    -1.87
     hurried
    -1.85
     rushed
    -1.84
     hurry
    -1.82
     Rapid
    -1.75
    Rapid
    -1.70
     rushing
    -1.67
    rapid
    -1.62
    Quick
    -1.60
    POSITIVE LOGITS
    IsMutable
    0.58
    曖昧さ回避
    0.56
     Nagasaki
    0.56
     propOrder
    0.53
    CppMethod
    0.52
    niająca
    0.50
    otoro
    0.50
    meau
    0.50
    ikistan
    0.50
     Архиви
    0.48
    Activations Density 2.377%

    No Known Activations