© 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. 14246
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are conceptually grouped as "things"

    oai_token-act-pair · gemini-2.0-flash

    lists

    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
     houſe
    -0.81
     Kinds
    -0.75
    Kind
    -0.74
     soort
    -0.73
     pleaſure
    -0.71
     kinds
    -0.71
    kinds
    -0.69
     Paglinawan
    -0.65
     stiefel
    -0.64
     nakalista
    -0.63
    POSITIVE LOGITS
     يتيمه
    0.65
     li
    0.59
    ,
    0.52
    ngilizce
    0.52
    udis
    0.51
    ikyuu
    0.50
     Bal
    0.48
    openSession
    0.48
     l
    0.48
     na
    0.48
    Activations Density 3.974%

    No Known Activations