© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6358
    Prev
    Next
    INDEX
    Explanations

    code snippets containing the keyword "err" and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    Code with error handling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     problemen
    -0.58
    Problems
    -0.57
     problèmes
    -0.57
     difficultés
    -0.56
     Problems
    -0.55
    ();)
    -0.55
    DECREF
    -0.54
     problème
    -0.54
     trouble
    -0.54
     problem
    -0.54
    POSITIVE LOGITS
     ujednoznacz
    0.62
    исленность
    0.58
     utafitiHapana
    0.54
    
    0.53
    談社
    0.53
    windowFixed
    0.52
    UnitTesting
    0.52
    expose
    0.51
    \{\\
    0.51
    rawValue
    0.50
    Activations Density 0.259%

    No Known Activations