© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214063
    Prev
    Next
    INDEX
    Explanations

    people authors

    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_50_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
     fences
    0.41
     હવા
    0.41
     fenced
    0.39
    蘅
    0.37
    IER
    0.37
    ierten
    0.36
    tert
    0.36
    era
    0.36
    ങ്
    0.36
     mon
    0.35
    POSITIVE LOGITS
    Meg
    0.40
     सूक्ष्म
    0.37
    গু
    0.36
    .>
    0.36
     گزارش
    0.36
    索引
    0.36
    Mega
    0.36
    ಐ
    0.36
     šk
    0.35
     subtlet
    0.35
    Activations Density 0.001%

    No Known Activations