© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6071
    Prev
    Next
    INDEX
    Explanations

    mentions of genes or proteins in scientific text

    oai_token-act-pair · gemini-2.0-flash

    gene symbols or labels

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

    Letters

    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
     myſelf
    -1.77
     Monfieur
    -1.72
     itſelf
    -1.65
     themſelves
    -1.55
     houſe
    -1.55
     purpoſe
    -1.52
     pleaſure
    -1.51
     Efq
    -1.49
     Jefus
    -1.48
     Houſe
    -1.47
    POSITIVE LOGITS
     E
    0.74
     F
    0.72
     G
    0.71
     P
    0.70
     C
    0.69
     T
    0.67
     M
    0.66
     K
    0.66
    ftagPool
    0.65
     H
    0.62
    Activations Density 7.678%

    No Known Activations