© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59433
    Prev
    Next
    INDEX
    Explanations

    ev, wi, van, vi, evo, ève

    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_2_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
    ات
    1.29
    al
    1.28
    。
    1.14
    op
    1.06
    aan
    1.02
    iędzy
    1.02
    จะ
    1.01
    िया
    0.99
    k
    0.98
    وم
    0.97
    POSITIVE LOGITS
    자
    1.00
    ro
    0.98
    로
    0.96
     increases
    0.95
    у
    0.94
     insults
    0.93
    ਰ
    0.93
    தம்ப
    0.92
    °)
    0.91
     fossils
    0.91
    Activations Density 0.000%

    No Known Activations