© 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
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 6264
    Prev
    Next
    INDEX
    Explanations

    technical or code symbols

    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_44_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
    །
    0.45
    ახ
    0.40
     минут
    0.39
    וני
    0.39
     महि
    0.37
    ብዙ
    0.36
    ρει
    0.36
     nedostat
    0.36
     optically
    0.36
    이나
    0.36
    POSITIVE LOGITS
    ﻹ
    0.48
    ಟ್‌
    0.47
     hâ
    0.47
     Café
    0.47
    Mâ
    0.47
    ïdes
    0.46
    ITÉ
    0.46
    vén
    0.46
     côte
    0.45
     رؤ
    0.45
    Activations Density 0.211%

    No Known Activations