© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9946
    Prev
    Next
    INDEX
    Explanations

    a word followed by a mostly grammatical word or symbol such as "be", "them", "is", "a", "in", "on"

    oai_token-act-pair · gemini-2.0-flash

    continuing excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Cybersecurity
    -0.79
     Malaria
    -0.77
     Tuberculosis
    -0.75
     Hypertension
    -0.74
     Gymnastics
    -0.73
     Psychotherapy
    -0.73
     Autism
    -0.73
     Apoptosis
    -0.73
     Genomics
    -0.73
     Dinosaurs
    -0.72
    POSITIVE LOGITS
     Place
    0.91
    Place
    0.88
     Line
    0.81
     Cut
    0.79
     Pass
    0.77
     Spot
    0.76
    Spot
    0.75
     Side
    0.75
     Set
    0.73
     Step
    0.73
    Activations Density 44.321%

    No Known Activations