© 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. 80474
    Prev
    Next
    INDEX
    Explanations

    your answer

    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
    DummyView
    0.41
     प्रमेय
    0.39
     temper
    0.37
     hemicontinuous
    0.37
    จะเป็น
    0.37
     deth
    0.36
     endow
    0.36
    雋
    0.36
     clothe
    0.36
     refine
    0.35
    POSITIVE LOGITS
     Tie
    0.43
     Linking
    0.39
     списка
    0.39
    列表
    0.38
    ֻ
    0.38
     Carlsbad
    0.38
     Cue
    0.37
    Stud
    0.36
     prosecuting
    0.36
     Cook
    0.36
    Activations Density 0.001%

    No Known Activations