© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77006
    Prev
    Next
    INDEX
    Explanations

    ImGui setup

    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_31_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
    स्क्र
    0.31
     ഇറ
    0.28
     Merrill
    0.28
    郃
    0.28
     cid
    0.28
     Disco
    0.28
    에서도
    0.28
     attainable
    0.28
    𝐷
    0.28
    Ep
    0.27
    POSITIVE LOGITS
     stuff
    0.47
     paraphernalia
    0.44
     باقی
    0.38
     hallmarks
    0.36
     باقي
    0.35
    stuff
    0.34
     subplot
    0.34
     infrastructure
    0.33
     বাকি
    0.33
    Added
    0.33
    Activations Density 0.156%

    No Known Activations