© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    sentences using multiple commas and the word "and"

    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
    Personendaten
    -0.88
    makeText
    -0.69
    GEBURTSDATUM
    -0.59
     dataSnapshot
    -0.55
    ClickListener
    -0.53
    VersionUID
    -0.52
     invokingState
    -0.49
    Personensuche
    -0.49
     disambiguazione
    -0.48
    deten
    -0.48
    POSITIVE LOGITS
    kasa
    0.55
     stelt
    0.54
     nennt
    0.54
    kso
    0.51
    Tarih
    0.50
     pourrait
    0.50
     sate
    0.49
     الرخصة
    0.49
    espero
    0.49
    nmgp
    0.48
    Activations Density 2.886%

    No Known Activations