© 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. 15632
    Prev
    Next
    INDEX
    Explanations

    passages describing the construction or history of a mechanical device or chemical procedure.

    oai_token-act-pair · gemini-2.0-flash

    various forms of the word "made"

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

    made

    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
    
    -0.76
     &___
    -0.65
     surla
    -0.63
     jsPsych
    -0.63
     للاسماء
    -0.60
    expandindo
    -0.58
    ]=>
    -0.57
    脚注の使い方
    -0.57
     Rumuni
    -0.56
     defStyleAttr
    -0.56
    POSITIVE LOGITS
     made
    1.78
    made
    1.51
     Made
    1.49
    Made
    1.38
     MADE
    1.34
     gemaakt
    1.14
     feita
    1.10
    MADE
    1.09
     faite
    1.07
     hecha
    1.07
    Activations Density 1.644%

    No Known Activations