© 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. 13826
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and syntax

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    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
    GEBURTSDATUM
    -1.08
    tonode
    -1.05
    ^(@)
    -1.04
     myſelf
    -1.03
     '\\;'
    -1.02
    NUMX
    -1.02
     themſelves
    -1.01
     himſelf
    -0.99
    EndGlobalSection
    -0.97
    iastes
    -0.96
    POSITIVE LOGITS
     
    0.56
     ​​
    0.50
     All
    0.41
     On
    0.40
     For
    0.40
     «
    0.38
     }}}
    0.37
      
    0.36
    ))),
    0.34
     H
    0.34
    Activations Density 2.179%

    No Known Activations