© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    a variety of common words that appear in technical and legal writing.

    oai_token-act-pair · gemini-2.0-flash

    actions related to placement or storing

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

    put/send somewhere

    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
    kregen
    -0.51
     hijas
    -0.51
    aryti
    -0.50
     touristes
    -0.49
     ujednoznacz
    -0.48
     væ
    -0.48
     vérit
    -0.48
     الرخصة
    -0.48
     ongles
    -0.47
    获取
    -0.47
    POSITIVE LOGITS
     put
    1.22
     placed
    1.15
     deposited
    1.03
     Put
    1.00
     sent
    1.00
    put
    1.00
     PUT
    0.95
     Placed
    0.93
     send
    0.93
     stored
    0.93
    Activations Density 6.129%

    No Known Activations