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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15242
    Prev
    Next
    INDEX
    Explanations

    mathematical articles with theorems, proofs, functions, probabilities, projections and related terms

    oai_token-act-pair · gemini-2.0-flash

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     myſelf
    -0.96
     itſelf
    -0.92
     leaſt
    -0.90
     faſt
    -0.90
     ProtoMessage
    -0.87
     becauſe
    -0.84
     Anſ
    -0.84
     neceffary
    -0.82
    ſelf
    -0.82
     themſelves
    -0.82
    POSITIVE LOGITS
     process
    0.54
     tem
    0.49
     rule
    0.49
     e
    0.49
     P
    0.47
     p
    0.47
     function
    0.46
     g
    0.46
     n
    0.46
     vi
    0.45
    Activations Density 5.189%

    No Known Activations