© 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. 4632
    Prev
    Next
    INDEX
    Explanations

    cases where general words and phrases are used to emphasize how easy or convenient something is

    oai_token-act-pair · gemini-2.0-flash

    simple

    np_max-act-logits · 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
     easily
    -2.11
    easily
    -2.06
     Easily
    -1.95
    Easily
    -1.80
     fácilmente
    -1.65
     facilmente
    -1.59
    Easy
    -1.55
     easy
    -1.54
     Easy
    -1.50
     facilement
    -1.50
    POSITIVE LOGITS
     simple
    1.39
    simple
    1.27
     simples
    1.20
     semplici
    1.18
     simpler
    1.07
     semplice
    1.07
     Simple
    1.05
    Simple
    1.03
     simplest
    0.99
     simpel
    0.91
    Activations Density 4.230%

    No Known Activations