© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3660
    Prev
    Next
    INDEX
    Explanations

    abbreviations and terminology related to biomedical research and lab work

    oai_token-act-pair · gemini-2.0-flash

    Scientific analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     مرئيه
    -0.66
     réfrig
    -0.59
     @"/
    -0.58
     forcément
    -0.56
     genoux
    -0.55
     doigt
    -0.54
     faveur
    -0.54
     jouets
    -0.53
     extré
    -0.53
     mauvaises
    -0.52
    POSITIVE LOGITS
     airfoil
    0.62
     perfusion
    0.61
     albedo
    0.61
     MSDS
    0.60
     effusion
    0.60
     anhydride
    0.60
     ablation
    0.60
     anisotropy
    0.60
     IUPAC
    0.60
     dehydrogenase
    0.59
    Activations Density 25.233%

    No Known Activations