© 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. 1584
    Prev
    Next
    INDEX
    Explanations

    symbols and terms frequently used when studying biology, chemistry, genetics, and medical research

    oai_token-act-pair · gemini-2.0-flash

    Scientific/mathematical descriptions

    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
     SG
    -1.18
     SB
    -1.16
     SF
    -1.16
     SN
    -1.15
     SJ
    -1.14
    SF
    -1.13
     SM
    -1.13
     SC
    -1.13
     SD
    -1.12
     SP
    -1.11
    POSITIVE LOGITS
     الرياضيه
    0.44
    lccn
    0.42
     متعلقه
    0.42
    Autoritní
    0.42
    GraphicsUnit
    0.41
    彿
    0.40
    ároz
    0.39
    Décès
    0.39
    Inflater
    0.39
     defaultstate
    0.38
    Activations Density 16.416%

    No Known Activations