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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    words that are frequently used as prepositions or conjunctions, along with some nouns

    oai_token-act-pair · gemini-2.0-flash

    Products

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    saraba
    -0.59
    ReusableCell
    -0.56
     dieux
    -0.54
     auroit
    -0.52
     élu
    -0.52
     vym
    -0.52
     traseira
    -0.51
     systeem
    -0.51
     étoit
    -0.51
     métallique
    -0.50
    POSITIVE LOGITS
     pillows
    0.60
     jewelry
    0.57
     clothing
    0.57
     fertiliser
    0.57
     paper
    0.57
     fertilizer
    0.56
     tableware
    0.54
     clothes
    0.53
     furniture
    0.52
     carpet
    0.52
    Activations Density 4.252%

    No Known Activations