© 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. 15469
    Prev
    Next
    INDEX
    Explanations

    a variety of seemingly unrelated words or punctuation, suggesting it may be a failed neuron

    oai_token-act-pair · 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
     Next
    -0.63
     We
    -0.62
     He
    -0.59
     First
    -0.58
    '],
    -0.57
     незавершена
    -0.57
    `,
    -0.57
     Він
    -0.56
    ")){
    -0.54
     Он
    -0.53
    POSITIVE LOGITS
     Buying
    0.67
     <<<<<<<<<<<<<<
    0.63
    Buying
    0.63
     Selling
    0.59
     czyn
    0.59
    RemoveField
    0.59
    appé
    0.57
     demandent
    0.57
     Handling
    0.57
    Picking
    0.57
    Activations Density 8.726%

    No Known Activations