© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10251
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and other quantities

    oai_token-act-pair · gemini-2.0-flash

    numerical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     (
    -0.38
      
    -0.38
    <eos>
    -0.35
    ↵
    -0.34
    !
    -0.34
     I
    -0.32
     H
    -0.32
     P
    -0.32
     at
    -0.32
     M
    -0.32
    POSITIVE LOGITS
     Majefty
    1.63
     ―――――
    1.54
     Efq
    1.51
     Monfieur
    1.51
     doubtnut
    1.48
     Theſe
    1.47
     itſelf
    1.45
     myſelf
    1.45
    parsedMessage
    1.44
    ſelves
    1.43
    Activations Density 2.438%

    No Known Activations