© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9341
    Prev
    Next
    INDEX
    Explanations

    common short words.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "brand"

    np_token-act-pair-logits · gpt-4o-mini
    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
     يتيمه
    -0.56
    μφωνα
    -0.55
    Datuak
    -0.51
     referenties
    -0.49
    Hentet
    -0.48
     externi
    -0.47
    kuuta
    -0.47
     excès
    -0.46
    はじめに
    -0.45
     användas
    -0.44
    POSITIVE LOGITS
     brand
    0.95
    brand
    0.73
     Brand
    0.68
     BRAND
    0.65
    ParallelGroup
    0.62
    mybatisplus
    0.61
    __':
    0.61
    Brand
    0.61
    BRAND
    0.60
    therefore
    0.60
    Activations Density 1.026%

    No Known Activations