© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4629
    Prev
    Next
    INDEX
    Explanations

    code fragments showing assignments and operators like =, <-, + and /

    oai_token-act-pair · gemini-2.0-flash

    assignment operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AccessorTable
    -0.90
     myſelf
    -0.77
     itſelf
    -0.75
     leaſt
    -0.71
     }}$}
    -0.70
    ſhip
    -0.68
     Jefus
    -0.68
     becauſe
    -0.68
    Autoritní
    -0.67
     */;
    -0.66
    POSITIVE LOGITS
    IBOutlet
    0.61
     den
    0.57
    ,
    0.52
     Den
    0.50
    Den
    0.49
    avras
    0.47
    olyb
    0.47
     bes
    0.46
     he
    0.46
     endwhile
    0.46
    Activations Density 12.579%

    No Known Activations