© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    abbreviations or symbols followed by numbers, often within a scientific context

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     feroit
    -1.59
     avoient
    -1.57
     étoit
    -1.56
     auroit
    -1.55
     étoient
    -1.50
     pouvoit
    -1.46
     Anſ
    -1.41
     myſelf
    -1.40
     Efq
    -1.37
     himſelf
    -1.36
    POSITIVE LOGITS
     
    0.91
      
    0.82
    ↵
    0.67
    -
    0.60
     “
    0.60
    ...
    0.59
    ↵↵
    0.59
     "
    0.56
    ,
    0.56
     A
    0.55
    Activations Density 47.676%

    No Known Activations