© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 9858
    Prev
    Next
    INDEX
    Explanations

    a mix of legal terminology, rap lyrics about conflict and struggle, and medical terminology, especially where they contain uncommon characters or formatting

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     and
    -0.76
     to
    -0.69
     `
    -0.65
     the
    -0.65
     or
    -0.63
     $
    -0.63
     in
    -0.61
     “
    -0.59
     (
    -0.59
     [
    -0.59
    POSITIVE LOGITS
     Efq
    0.76
     تضيفلها
    0.75
     AspNetCore
    0.73
     nakalista
    0.71
    MLLoader
    0.68
     engraçadas
    0.67
     שוליים
    0.63
     anún
    0.61
     CommonModule
    0.60
     HEW
    0.58
    Activations Density 9.938%

    No Known Activations