© 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. 11762
    Prev
    Next
    INDEX
    Explanations

    code snippets with Java-like syntax, especially method declarations and keywords like "public", "void", "run", "Override", "OnClickListener", "final", and "private".

    oai_token-act-pair · gemini-2.0-flash

    Public

    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
     myſelf
    -1.84
     Efq
    -1.75
     itſelf
    -1.63
     Jefus
    -1.61
    ſelf
    -1.60
     themſelves
    -1.59
     himſelf
    -1.57
     ་་
    -1.55
    ſelves
    -1.55
     Majefty
    -1.55
    POSITIVE LOGITS
     
    1.08
     T
    0.79
     in
    0.71
    ,
    0.71
     v
    0.70
     y
    0.68
     p
    0.67
    ↵↵
    0.66
     E
    0.66
     qu
    0.66
    Activations Density 2.456%

    No Known Activations