© 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. 15007
    Prev
    Next
    INDEX
    Explanations

    capital letters "U" followed by one or two lowercase letters

    oai_token-act-pair · gemini-2.0-flash

    Technical or mixed content

    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
    brtc
    -0.50
     resistenza
    -0.48
    ched
    -0.46
    ритори
    -0.45
     Pedersen
    -0.44
    glBind
    -0.44
    chado
    -0.43
    ForResult
    -0.43
     up
    -0.42
    estre
    -0.42
    POSITIVE LOGITS
    Tikang
    0.89
    sizeCache
    0.73
     WAP
    0.71
     gyhoeddwyd
    0.68
     ProtoMessage
    0.64
    ніципа
    0.64
     '\\;'
    0.63
    colgroup
    0.63
     Pliocene
    0.63
    AndEndTag
    0.63
    Activations Density 0.353%

    No Known Activations