© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11068
    Prev
    Next
    INDEX
    Explanations

    positive descriptive words

    oai_token-act-pair · gemini-2.0-flash

    superlative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     more
    -1.72
     greater
    -1.55
     lebih
    -1.51
    more
    -1.48
    More
    -1.42
     Lebih
    -1.41
     faster
    -1.38
     stronger
    -1.38
     More
    -1.36
     better
    -1.35
    POSITIVE LOGITS
     most
    1.29
    most
    1.13
    Most
    0.98
     Most
    0.97
     least
    0.90
     MOST
    0.90
    MOST
    0.88
    least
    0.82
     rarest
    0.81
    kháu
    0.71
    Activations Density 0.743%

    No Known Activations