© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14704
    Prev
    Next
    INDEX
    Explanations

    abbrevations, acronyms, and codes used in healthcare, medical texts, and other computer engineering and network contexts

    oai_token-act-pair · gemini-2.0-flash

    Abbreviations and acronyms

    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
     Efq
    -0.84
     itſelf
    -0.74
     للمعارف
    -0.72
     Theſe
    -0.70
    makeText
    -0.69
    awtextra
    -0.69
     Económica
    -0.68
     Houſe
    -0.66
    TagMode
    -0.66
    tvguidetime
    -0.66
    POSITIVE LOGITS
     He
    0.57
    matchCondition
    0.56
     AL
    0.51
     me
    0.50
     Qu
    0.49
     S
    0.48
     Che
    0.47
     ME
    0.47
     NE
    0.47
     A
    0.47
    Activations Density 3.802%

    No Known Activations