© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13909
    Prev
    Next
    INDEX
    Explanations

    technical terms related to screens, fields, or nucleic acids and also finds mentions of left and right

    oai_token-act-pair · gemini-2.0-flash

    left and right side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     مشين
    -0.82
    DoubleQuotes
    -0.77
    évaluateur
    -0.69
     الرياضيه
    -0.65
     تضيفلها
    -0.63
    
    -0.62
    anyahu
    -0.60
     Signalez
    -0.60
     AspNetCore
    -0.59
     BoxFit
    -0.59
    POSITIVE LOGITS
    roek
    0.56
    fjspx
    0.52
    مج
    0.51
    Itoa
    0.51
    MLLoader
    0.51
     τό
    0.50
    Datuak
    0.49
     gyak
    0.48
     kés
    0.47
    abord
    0.46
    Activations Density 1.513%

    No Known Activations