© 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. 9160
    Prev
    Next
    INDEX
    Explanations

    places

    oai_token-act-pair · 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
    MemoryWarning
    -1.02
    ագրություններ
    -0.69
     Normdatei
    -0.66
    WriteBarrier
    -0.62
     Walkover
    -0.60
    ^(@)
    -0.59
    Билгалдахарш
    -0.59
    SBATCH
    -0.59
    críbete
    -0.57
    awakeFromNib
    -0.57
    POSITIVE LOGITS
     cocoon
    0.56
     consulate
    0.54
     Bankers
    0.50
     Bison
    0.48
     Ennis
    0.48
     Consulate
    0.47
     oaks
    0.47
     Balboa
    0.47
     crystals
    0.46
     biceps
    0.46
    Activations Density 2.706%

    No Known Activations