© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43905
    Prev
    Next
    INDEX
    Explanations

    death penalty

    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_13_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
     fiasco
    0.45
    <0xAC>
    0.38
    elses
    0.35
    브
    0.35
     investigate
    0.34
    จ
    0.34
    بر
    0.34
     workforce
    0.34
     prestazioni
    0.34
    <0xA3>
    0.33
    POSITIVE LOGITS
     জেল
    0.39
    CodeableConcept
    0.35
    িকাল
    0.34
     கம்ப
    0.34
    FormProvider
    0.34
    秞
    0.34
     Dharmendra
    0.33
    NavLink
    0.32
     गुलाब
    0.32
     Shabd
    0.32
    Activations Density 0.001%

    No Known Activations