© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14014
    Prev
    Next
    INDEX
    Explanations

    text discussing molecular studies or analyses

    oai_token-act-pair · gemini-2.0-flash

    molecular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    …
    -0.88
    .
    -0.74
    ing
    -0.71
     …
    -0.67
     ‘
    -0.65
    ……
    -0.65
    ↵
    -0.64
     https
    -0.62
    -
    -0.61
    -0.61
    POSITIVE LOGITS
     myſelf
    1.64
     Jefus
    1.59
     himſelf
    1.58
     pleaſure
    1.55
     Monfieur
    1.55
     itſelf
    1.54
     themſelves
    1.52
     purpoſe
    1.50
     feroit
    1.45
     Efq
    1.45
    Activations Density 2.666%
    No Known Activations