© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221299
    Prev
    Next
    INDEX
    Explanations

    contrast or unexpected action

    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
    Negative Logits
    ,
    0.42
    ،
    0.42
    ,\
    0.40
    .$,
    0.39
    처럼
    0.38
    ',
    0.38
     }}
    0.37
     ],
    0.37
    ],\
    0.37
     },
    0.36
    POSITIVE LOGITS
     сверх
    0.40
     общественного
    0.40
     bequem
    0.38
     вважа
    0.37
    maier
    0.37
     kuasa
    0.34
    Officials
    0.34
    ինչ
    0.34
    ंसिल
    0.34
     overcame
    0.34
    Activations Density 0.006%

    No Known Activations