© 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. 13590
    Prev
    Next
    INDEX
    Explanations

    uses of code, sports competitions, math equations, and medical procedures

    oai_token-act-pair · gemini-2.0-flash

    Roman numerals

    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
     CreateTagHelper
    -0.82
    SequentialGroup
    -0.81
    Vidite
    -0.77
    ChildScrollView
    -0.73
    сылкі
    -0.69
     незавершена
    -0.69
    Према
    -0.68
    下载附件
    -0.67
     BoxFit
    -0.66
    Personensuche
    -0.65
    POSITIVE LOGITS
     II
    1.24
     III
    1.14
     IV
    0.98
    III
    0.90
     Two
    0.89
     #
    0.89
    II
    0.85
     One
    0.85
     VII
    0.82
     TWO
    0.79
    Activations Density 8.329%

    No Known Activations