© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13187
    Prev
    Next
    INDEX
    Explanations

    sentence punctuation and discourse markers

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    ObjectContext
    -0.65
     coû
    -0.54
     AssemblyCompany
    -0.52
     noyau
    -0.46
    IsMutable
    -0.46
     oggetto
    -0.46
    matchCondition
    -0.45
     règne
    -0.45
     Rankin
    -0.44
     Parcelable
    -0.44
    POSITIVE LOGITS
     besides
    2.08
    besides
    1.94
    Besides
    1.92
     Besides
    1.90
     plus
    1.66
     Plus
    1.51
    plus
    1.45
    Plus
    1.44
     PLUS
    1.39
     além
    1.37
    Activations Density 1.409%

    No Known Activations