© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10731
    Prev
    Next
    INDEX
    Explanations

    words frequently used in narrative storytelling or explanations of a past event involving people

    oai_token-act-pair · gemini-2.0-flash

    non-English or system-related terms

    np_token-act-pair-logits · gpt-4o-mini

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     S
    -0.39
     
    -0.35
    ju
    -0.35
    ie
    -0.33
    杜
    -0.33
     پی
    -0.33
     zá
    -0.32
     plazo
    -0.32
    概
    -0.32
     al
    -0.32
    POSITIVE LOGITS
     الرياضيه
    1.10
     ostavi
    1.02
    WithIOException
    0.98
     EconPapers
    0.96
    ValueStyle
    0.96
     CreateTagHelper
    0.94
     betweenstory
    0.94
    Билгалдахарш
    0.93
     समीक्षक
    0.93
    GEBURTSDATUM
    0.92
    Activations Density 13.848%

    No Known Activations