© 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. 5313
    Prev
    Next
    INDEX
    Explanations

    file system operations using the `os` module in python, with emphasis on path construction

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Rigidbody
    -0.60
    Rigidbody
    -0.59
     CanadaChoose
    -0.56
    IBOutlet
    -0.54
    rrggbb
    -0.52
     front
    -0.51
     Front
    -0.50
     handleMessage
    -0.49
    biles
    -0.49
     Path
    -0.49
    POSITIVE LOGITS
     Suf
    0.61
     Esau
    0.59
     Platon
    0.59
    consulté
    0.58
     Myra
    0.58
     חיצוניים
    0.58
    
    0.58
     Athenians
    0.55
     RSSSF
    0.54
     hybrids
    0.53
    Activations Density 0.341%

    No Known Activations