© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5371
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and notation

    oai_token-act-pair · gemini-2.0-flash

    symbolic notations or special characters

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

    mathematical text

    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
    fromnode
    -0.66
    ParallelGroup
    -0.66
    ArrowToggle
    -0.54
    TagMode
    -0.53
     հղումներ
    -0.51
     linkovi
    -0.50
     EconPapers
    -0.49
    AndEndTag
    -0.49
    AutoresizingMask
    -0.49
    krivning
    -0.48
    POSITIVE LOGITS
     cdti
    0.63
     -)
    0.58
    \%)
    0.58
    %).
    0.55
    ();)
    0.54
     Cæsar
    0.54
    poh
    0.53
    :)
    0.53
     uſed
    0.52
    %)
    0.52
    Activations Density 4.640%

    No Known Activations