© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8277
    Prev
    Next
    INDEX
    Explanations

    references to or direct invocations of God, as well as to sounds like yells

    oai_token-act-pair · gemini-2.0-flash

    Please and Give

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    出版年
    -0.75
    
    -0.57
    tagext
    -0.56
    posedge
    -0.56
    ')";
    -0.55
    fjspx
    -0.54
    initWithFrame
    -0.52
    '])->
    -0.52
     Título
    -0.51
     Мексичка
    -0.51
    POSITIVE LOGITS
     please
    1.16
     Please
    1.09
     PLEASE
    1.00
    Please
    0.96
     Give
    0.92
    please
    0.88
     give
    0.86
    Give
    0.82
    PLEASE
    0.81
    give
    0.77
    Activations Density 0.937%

    No Known Activations