© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16125
    Prev
    Next
    INDEX
    Explanations

    instances in programming contexts where an exception is thrown.

    oai_token-act-pair · gemini-2.0-flash

    throw

    np_max-act · gemini-2.0-flash

    throw

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     to
    -0.68
     di
    -0.67
     in
    -0.64
    2
    -0.63
     ,
    -0.63
    ,
    -0.62
    …
    -0.60
    {~
    -0.59
     –
    -0.58
    <eos>
    -0.58
    POSITIVE LOGITS
     myſelf
    1.71
     Theſe
    1.70
     itſelf
    1.59
     Monfieur
    1.59
     Jefus
    1.55
     whoſe
    1.55
     ſeveral
    1.47
     becauſe
    1.47
     iſt
    1.46
    ſelf
    1.42
    Activations Density 1.802%

    No Known Activations