© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4645
    Prev
    Next
    INDEX
    Explanations

    reserved words, symbols and indentation in Python code

    oai_token-act-pair · gemini-2.0-flash

    code with import statements

    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
    ]")]
    -0.70
    parsedMessage
    -0.70
    Numerade
    -0.60
      (
    -0.60
    styleType
    -0.59
    Lycka
    -0.58
    Pratique
    -0.58
     Савезне
    -0.57
    enumi
    -0.57
     wireType
    -0.56
    POSITIVE LOGITS
     proletariat
    0.62
     laborers
    0.58
     pietre
    0.56
     labourers
    0.54
     Ignorance
    0.54
     mimi
    0.53
    path
    0.52
    ophosphate
    0.52
     htons
    0.52
    Демографія
    0.51
    Activations Density 2.770%

    No Known Activations