© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66549
    Prev
    Next
    INDEX
    Explanations

    for demonstration purposes

    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_41_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
     ساعة
    0.38
    ष्मा
    0.38
    小便
    0.37
    ত্যাশিত
    0.36
    굉
    0.35
     危
    0.35
    ytail
    0.35
    ([]);
    0.34
     பட்டியல்
    0.34
    polls
    0.34
    POSITIVE LOGITS
     purposes
    1.62
     Purposes
    1.40
    目的
    1.28
     목적
    1.08
    的目的
    1.04
     целей
    1.00
     purpose
    1.00
     उद्देश्यों
    0.99
    Purpose
    0.99
     amaç
    0.98
    Activations Density 0.012%

    No Known Activations