© 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. 4725
    Prev
    Next
    INDEX
    Explanations

    month and date references, often near time stamps

    oai_token-act-pair · 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
     betweenstory
    -1.24
     defaultstate
    -1.19
    rungsseite
    -1.15
    ſelf
    -1.14
    UnusedPrivate
    -1.13
    AddTagHelper
    -1.13
    ſelves
    -1.11
     Efq
    -1.11
     nahilalakip
    -1.09
     houſe
    -1.07
    POSITIVE LOGITS
     
    0.64
    2
    0.54
      
    0.52
     For
    0.50
    ,
    0.48
     as
    0.48
     ex
    0.47
     min
    0.46
     (
    0.46
     y
    0.46
    Activations Density 2.641%

    No Known Activations