© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219053
    Prev
    Next
    INDEX
    Explanations

    Purposes, Input, Adv

    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_16_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ,
    0.49
    athed
    0.47
    arbeit
    0.46
     fours
    0.46
    Μ
    0.45
    AL
    0.44
    pores
    0.44
    Argument
    0.43
     typos
    0.43
     halten
    0.43
    POSITIVE LOGITS
     médico
    0.48
     medico
    0.48
     Công
    0.48
     ನಾನು
    0.47
     North
    0.47
    扨
    0.47
     Groundwater
    0.46
     dịch
    0.45
    墮
    0.45
     사진
    0.44
    Activations Density 0.000%

    No Known Activations