© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3436
    Prev
    Next
    INDEX
    Explanations

    occurrences of "exception" and phrases using the word, especially with the word than

    oai_token-act-pair · gemini-2.0-flash

    exception

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    digkeit
    -0.41
    ifornia
    -0.41
    ielsen
    -0.40
    ViewInit
    -0.39
    appé
    -0.39
    торов
    -0.38
    glie
    -0.38
     Galo
    -0.38
     органов
    -0.38
    LabelTagHelper
    -0.37
    POSITIVE LOGITS
     exceptions
    2.48
     exception
    2.38
     Exceptions
    2.11
     excep
    1.94
    exception
    1.89
     EXCEPT
    1.87
     Exception
    1.83
    exceptions
    1.80
    Exceptions
    1.79
     excepción
    1.78
    Activations Density 2.184%

    No Known Activations