© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49194
    Prev
    Next
    INDEX
    Explanations

    say discrimination

    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_55_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
    별
    0.61
     discriminating
    0.52
     discriminatory
    0.52
     discrimin
    0.45
    区分
    0.40
     discriminate
    0.39
     discriminated
    0.39
     구분
    0.38
     distin
    0.37
    贱
    0.36
    POSITIVE LOGITS
     disk
    2.11
     disc
    2.02
     Disk
    1.90
    disk
    1.88
     диск
    1.87
    Disk
    1.83
    disc
    1.65
    ディスク
    1.56
     차
    1.52
     disks
    1.48
    Activations Density 0.035%

    No Known Activations