© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15378
    Prev
    Next
    INDEX
    Explanations

    colors

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

    multiple words indicating a gathering of people and a fiery burst.

    oai_token-act-pair · gemini-2.0-flash

    colors

    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
    Negative Logits
    expandindo
    -0.93
    发表于
    -0.85
     externi
    -0.72
     nahilalakip
    -0.68
     المعيارى
    -0.66
     &___
    -0.63
     bezeichneter
    -0.61
     يتيمه
    -0.61
     EnglishChoose
    -0.60
     beginnetje
    -0.60
    POSITIVE LOGITS
     yellow
    0.65
     green
    0.65
     red
    0.64
     blue
    0.60
    yellow
    0.56
     white
    0.55
     pink
    0.54
    queryInterface
    0.54
     purple
    0.52
     multicolored
    0.51
    Activations Density 2.923%

    No Known Activations