© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1334
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to technical fields and hobbies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     qu
    -0.97
     sil
    -0.85
     ho
    -0.84
     ra
    -0.82
     ch
    -0.80
     sur
    -0.80
     fer
    -0.80
     ha
    -0.80
     ro
    -0.79
     se
    -0.78
    POSITIVE LOGITS
     avoient
    1.50
     auroit
    1.48
     vectorielles
    1.47
     étoient
    1.41
     feroit
    1.40
     spéciaux
    1.38
     définiti
    1.34
     scolaires
    1.32
     enfans
    1.30
     colorés
    1.30
    Activations Density 2.739%

    No Known Activations