© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132088
    Prev
    Next
    INDEX
    Explanations

    McKinsey

    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_1_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
    of
    1.59
    or
    1.34
    um
    1.09
    計画
    1.05
    at
    1.03
     fondness
    1.02
    ف
    1.01
    いた
    0.98
    ная
    0.97
    ۰
    0.97
    POSITIVE LOGITS
    j
    1.20
    لا
    1.09
     ২০
    1.05
    لي
    1.02
     allgemeinen
    1.00
    0.98
    ))
    0.96
     Erwachsene
    0.96
    ↵↵
    0.95
    2
    0.95
    Activations Density 0.000%

    No Known Activations