© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6759
    Prev
    Next
    INDEX
    Explanations

    the word "the" and other related words signifying a unique entity.

    oai_token-act-pair · gemini-2.0-flash

    nouns indicating importance or significance

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    сылкі
    -0.59
    ագրություններ
    -0.59
     constaté
    -0.58
    Hochspringen
    -0.57
    reportWebVitals
    -0.54
    tinyos
    -0.53
    clerview
    -0.50
    CppCodeGen
    -0.49
     fallu
    -0.49
     refusé
    -0.49
    POSITIVE LOGITS
     person
    0.66
     source
    0.60
     first
    0.60
     greatest
    0.58
    __(/*!
    0.57
     type
    0.57
     only
    0.56
     guy
    0.56
     wireType
    0.55
    greatest
    0.55
    Activations Density 1.000%

    No Known Activations