© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12533
    Prev
    Next
    INDEX
    Explanations

    bio followed by science/tech terms

    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
    ﻘ
    0.43
    IsDir
    0.42
     pricey
    0.40
    ຕົ
    0.39
    Frag
    0.39
    ्रेट
    0.39
     distra
    0.38
    Expensive
    0.38
     aliexpress
    0.37
     distracting
    0.37
    POSITIVE LOGITS
     pya
    0.39
    ्हे
    0.39
    urine
    0.39
    鐐
    0.38
    immediate
    0.38
     biologically
    0.37
     Chronicle
    0.37
     сал
    0.37
    chemicals
    0.36
    Chron
    0.35
    Activations Density 0.006%

    No Known Activations