© 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. 1556
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gemini-2.0-flash

    words related to large numbers or quantities

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

    numbers

    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
    一百
    -0.56
     millions
    -0.53
     milhões
    -0.52
     OMITBAD
    -0.51
    edin
    -0.47
     milioni
    -0.47
    百万
    -0.45
    ideos
    -0.45
     Millions
    -0.45
    millions
    -0.43
    POSITIVE LOGITS
     thousand
    0.82
    thou
    0.77
     thou
    0.75
     يتيمه
    0.74
     thousands
    0.70
    =$?
    0.68
    thousand
    0.66
     thon
    0.64
     Thousand
    0.60
     Thou
    0.60
    Activations Density 2.812%

    No Known Activations