© 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. 7304
    Prev
    Next
    INDEX
    Explanations

    words and short phrases related to chemistry, biology, and scientific research

    oai_token-act-pair · gemini-2.0-flash

    Scientific and biological contexts

    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
     participating
    -0.86
    managing
    -0.81
     managing
    -0.79
     returning
    -0.74
     migrating
    -0.73
     contributing
    -0.73
    Participating
    -0.72
     losing
    -0.71
     interacting
    -0.70
     controlling
    -0.69
    POSITIVE LOGITS
     holding
    0.55
     tearing
    0.54
    xtext
    0.52
     تضيفلها
    0.51
    
    0.51
     filling
    0.49
    Holding
    0.49
     flattening
    0.49
     Packing
    0.48
     narrowing
    0.47
    Activations Density 13.695%

    No Known Activations