© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12959
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation preceded by some of a collection of common words or phrases, and also related phrases about writing

    oai_token-act-pair · gemini-2.0-flash

    -ly adverbs

    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
     very
    -0.65
    StructEnd
    -0.65
    قایناق‌لار
    -0.57
     svært
    -0.57
    الحياه
    -0.56
    Népesség
    -0.53
    utnik
    -0.52
    AttributeName
    -0.51
     aveug
    -0.50
    seck
    -0.50
    POSITIVE LOGITS
     intelligently
    0.63
     smoothly
    0.61
     wisely
    0.59
     responsibly
    0.55
     safely
    0.55
     skillfully
    0.55
     confidently
    0.54
     patiently
    0.54
     comfortably
    0.54
     arşivlendi
    0.53
    Activations Density 19.706%

    No Known Activations