© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4052
    Prev
    Next
    INDEX
    Explanations

    the word "meta" and words that are close to it

    oai_token-act-pair · gemini-2.0-flash

    instances of "meta" or related terms

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

    meta

    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
    waitKey
    -0.66
    createComponent
    -0.60
    NOPQRST
    -0.59
    pplung
    -0.56
    amation
    -0.55
    ніципа
    -0.54
    derabad
    -0.54
    fetchone
    -0.53
    dafx
    -0.53
    انجليز
    -0.52
    POSITIVE LOGITS
    spesies
    0.47
    Viri
    0.46
    Și
    0.45
     agrí
    0.44
    万美元
    0.43
     ostavi
    0.43
     MediaQuery
    0.42
    SizeMode
    0.42
     Poplar
    0.42
     gouden
    0.41
    Activations Density 1.498%

    No Known Activations