© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    angle brackets

    oai_token-act-pair · gemini-2.0-flash

    Navigation elements

    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
     system
    -0.44
     archaeologist
    -0.43
     agency
    -0.42
     library
    -0.37
     museum
    -0.37
     company
    -0.37
     database
    -0.36
    dhism
    -0.36
     airline
    -0.36
     aquaculture
    -0.36
    POSITIVE LOGITS
     Road
    0.69
     MenuView
    0.68
     Bridge
    0.66
    numerusform
    0.66
     Theme
    0.66
     Mile
    0.66
     Square
    0.65
     Menu
    0.65
     Route
    0.65
     Edge
    0.65
    Activations Density 50.003%

    No Known Activations