© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    boxed substance or fat

    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
     DROP
    0.21
     drop
    0.19
     addition
    0.19
     drops
    0.18
     ब्लूटूथ
    0.18
    $\,.
    0.18
    䒿
    0.18
    DROP
    0.17
     Drop
    0.17
    δώ
    0.17
    POSITIVE LOGITS
     robuste
    0.21
    Penn
    0.20
    inni
    0.19
     economico
    0.19
    Robust
    0.18
    ابة
    0.18
    ىرى
    0.18
    icioso
    0.18
     Penn
    0.18
    挀
    0.18
    Activations Density 0.000%

    No Known Activations