© 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. 9376
    Prev
    Next
    INDEX
    Explanations

    passages discussing science and scientific concepts

    oai_token-act-pair · gemini-2.0-flash

    science-related topics

    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
     scientific
    -2.11
     science
    -1.99
    scientific
    -1.94
    science
    -1.88
     Science
    -1.88
     scientists
    -1.88
    Scientific
    -1.86
     Scientific
    -1.84
    Science
    -1.84
     scientist
    -1.81
    POSITIVE LOGITS
    Datuak
    0.66
    enumii
    0.65
    onAttach
    0.56
     typelib
    0.54
    addCriterion
    0.53
    VIAF
    0.52
     Goats
    0.52
    oa̍t
    0.51
    kuuta
    0.49
     Lattice
    0.48
    Activations Density 2.883%

    No Known Activations