© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219987
    Prev
    Next
    INDEX
    Explanations

    legal structure descriptions

    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
     увлека
    0.47
    并未
    0.43
    fid
    0.41
     delegate
    0.40
    の世界
    0.39
     playing
    0.39
     captains
    0.38
    ₁)
    0.37
     dost
    0.37
    backs
    0.37
    POSITIVE LOGITS
    竇
    0.42
     ভাঁ
    0.41
    URNIZ
    0.40
     جبر
    0.39
    उन
    0.38
     தாய
    0.38
    计算
    0.37
     خور
    0.37
     Suu
    0.37
    antibodies
    0.36
    Activations Density 0.001%

    No Known Activations