© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232757
    Prev
    Next
    INDEX
    Explanations

    inequality

    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_32_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
     ignor
    0.39
    力
    0.38
     powerless
    0.38
    increasing
    0.37
     pobreza
    0.35
     দারিদ্র
    0.35
     helpless
    0.35
    শরণ
    0.34
    Bu
    0.34
    lemon
    0.33
    POSITIVE LOGITS
     daños
    0.41
     gastronom
    0.41
    鳄
    0.40
     blushed
    0.39
    țiunea
    0.38
     wrinkles
    0.38
     radicals
    0.37
    âm
    0.37
     wrink
    0.37
    tie
    0.37
    Activations Density 0.003%

    No Known Activations