© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12922
    Prev
    Next
    INDEX
    Explanations

    words related to describing results in studies

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    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
    Egypte
    -0.55
     تضيفلها
    -0.55
     bezeichneter
    -0.55
    Somewhat
    -0.54
     Theſe
    -0.53
    的就是
    -0.52
     Justo
    -0.52
    suddenly
    -0.51
    eventually
    -0.50
    nothing
    -0.50
    POSITIVE LOGITS
    出版年
    0.66
    mybatisplus
    0.63
     itself
    0.63
     الاطلاع
    0.62
    FormTagHelper
    0.60
    ParallelGroup
    0.60
     AssemblyCulture
    0.58
    WriteTagHelper
    0.57
     themselves
    0.57
    实
    0.56
    Activations Density 3.921%

    No Known Activations