© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170972
    Prev
    Next
    INDEX
    Explanations

    chemical nomenclature prefixes

    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_20_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
     Kanji
    0.40
     investigation
    0.40
     ayuda
    0.38
    ධා
    0.38
     K
    0.36
     ligation
    0.36
    घु
    0.36
    疳
    0.36
    ADESH
    0.35
    আপ
    0.35
    POSITIVE LOGITS
     veldig
    0.43
     skiers
    0.40
     vélo
    0.39
     горе
    0.38
     নির্ব
    0.38
     города
    0.38
     Cinemas
    0.37
     Parr
    0.36
     リー
    0.36
     väldigt
    0.36
    Activations Density 0.001%

    No Known Activations