© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10133
    Prev
    Next
    INDEX
    Explanations

    usages of the word "it" when combined with words like "look", "sound", and "make"

    oai_token-act-pair · gemini-2.0-flash

    appearances seem deceiving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     seeming
    -1.69
     seemed
    -1.55
     sounding
    -1.45
     seem
    -1.39
     seems
    -1.38
    seemed
    -1.35
     appears
    -1.35
     Seems
    -1.34
     Appears
    -1.34
     appear
    -1.33
    POSITIVE LOGITS
     الرياضيه
    0.72
    DREN
    0.49
    Gdx
    0.47
    kolan
    0.45
    urons
    0.44
    łog
    0.43
    нус
    0.42
    Santis
    0.42
    rore
    0.42
    badah
    0.42
    Activations Density 0.325%

    No Known Activations