© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9127
    Prev
    Next
    INDEX
    Explanations

    math and code snippets

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    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
     TextFormField
    -0.70
     _$
    -0.67
     تضيفلها
    -0.66
     ElevatedButton
    -0.64
     незавершена
    -0.64
     auroit
    -0.60
     zelve
    -0.59
     étoit
    -0.57
     butterknife
    -0.57
     pouvoit
    -0.57
    POSITIVE LOGITS
     Se
    0.64
     game
    0.62
     plant
    0.61
     medical
    0.61
     culture
    0.60
     center
    0.60
     bank
    0.60
     market
    0.59
     Bank
    0.59
     real
    0.59
    Activations Density 20.179%

    No Known Activations