© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5289
    Prev
    Next
    INDEX
    Explanations

    throws exception types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    陏
    0.40
    鹜
    0.37
     happ
    0.37
    ToPlot
    0.37
     प्रॉब्लम
    0.36
     бас
    0.36
     Grandmother
    0.36
    秩
    0.36
    grandfather
    0.35
     grandfather
    0.35
    POSITIVE LOGITS
     interrupt
    0.52
    java
    0.52
     interrupted
    0.52
     java
    0.52
     interrump
    0.47
     unchecked
    0.46
    Interrupt
    0.46
     interrom
    0.43
    Inter
    0.43
    unchecked
    0.41
    Activations Density 0.004%

    No Known Activations