© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10010
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for matrices and arrays.

    oai_token-act-pair · gemini-2.0-flash

    uncommon words

    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
      
    -0.59
    ↵
    -0.59
     ap
    -0.53
     […]
    -0.52
     ra
    -0.52
     cu
    -0.51
     con
    -0.50
     co
    -0.50
     Co
    -0.50
     nu
    -0.50
    POSITIVE LOGITS
     Shakspeare
    1.16
     Cæsar
    1.15
     moschino
    1.13
     Anſ
    1.11
     scolaires
    1.02
     Shaksp
    1.01
     فريبيس
    0.99
     photolibrary
    0.96
     holotype
    0.93
    RectangleBorder
    0.91
    Activations Density 31.780%

    No Known Activations