© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14373
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "term" or other words relating to language.

    oai_token-act-pair · gemini-2.0-flash

    word or term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     word
    -0.71
     
    -0.57
    <eos>
    -0.51
     term
    -0.50
     equivalent
    -0.48
     label
    -0.48
     corresponding
    -0.48
     nu
    -0.48
    <bos>
    -0.47
     s
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.93
    AddTagHelper
    0.73
    PerformLayout
    0.73
     חיצוניים
    0.71
     فريبيس
    0.70
     Ordovician
    0.66
    aarrggbb
    0.65
     surla
    0.65
    fjspx
    0.63
    Portale
    0.63
    Activations Density 1.176%

    No Known Activations