© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5600
    Prev
    Next
    INDEX
    Explanations

    technical writing about instruments and ways of measuring them

    oai_token-act-pair · gemini-2.0-flash

    testing and measuring

    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
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.79
    ANTLR
    -0.73
    niosek
    -0.69
     contextLoads
    -0.65
     BoxDecoration
    -0.65
     betweenstory
    -0.63
     لينك
    -0.62
    TagHelper
    -0.58
     snippetHide
    -0.57
    BeginInit
    -0.57
    POSITIVE LOGITS
    出版年
    0.59
     lenker
    0.58
    cal
    0.51
     test
    0.50
     Dy
    0.47
    getProfile
    0.46
     measurements
    0.46
    test
    0.46
     performance
    0.46
    Хьажоргаш
    0.45
    Activations Density 2.519%

    No Known Activations