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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9801
    Prev
    Next
    INDEX
    Explanations

    scientific and medical texts related to cells, proteins, and treatments involving regulation, inhibition, and infection, often referencing other studies

    oai_token-act-pair · gemini-2.0-flash

    Scientific/biological processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     enfans
    -0.75
     ainfi
    -0.69
     Efq
    -0.67
    bibfield
    -0.66
    ſelf
    -0.65
     Majefty
    -0.63
     leçon
    -0.63
    citenamefont
    -0.62
    bibinfo
    -0.61
     vérit
    -0.61
    POSITIVE LOGITS
     pherom
    0.71
     sintering
    0.61
     lignin
    0.60
     estrogen
    0.57
     amyloid
    0.57
     emulsions
    0.56
     DMSO
    0.54
     turbidity
    0.54
     embry
    0.53
     saline
    0.53
    Activations Density 27.010%

    No Known Activations