© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152139
    Prev
    Next
    INDEX
    Explanations

    business and finance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    etaan
    0.45
    }}_
    0.45
     endorsing
    0.44
    álie
    0.42
     специа
    0.40
     继续
    0.40
     hii
    0.40
    slideDuplicate
    0.39
    ંમે
    0.39
    ération
    0.38
    POSITIVE LOGITS
     anew
    0.42
    Judge
    0.40
     Judge
    0.37
     assent
    0.37
    Mary
    0.35
     orbits
    0.34
    ற
    0.33
    义务
    0.33
     mary
    0.33
     rum
    0.32
    Activations Density 0.002%

    No Known Activations