© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9795
    Prev
    Next
    INDEX
    Explanations

    the word "El" or abbreviations, potentially in place names or organizations

    oai_token-act-pair · gemini-2.0-flash

    El

    np_max-act · gemini-2.0-flash

    El

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     El
    -2.05
     el
    -1.87
    El
    -1.84
     EL
    -1.23
     Els
    -0.84
     Ел
    -0.81
     els
    -0.81
    エル
    -0.80
     Эль
    -0.75
     Le
    -0.74
    POSITIVE LOGITS
     viață
    0.69
     étoient
    0.69
     pouvoit
    0.68
     feroit
    0.65
     distanciation
    0.64
     BIBSYS
    0.63
     avoient
    0.63
     auroit
    0.63
     marinho
    0.60
     étoit
    0.60
    Activations Density 0.699%

    No Known Activations