© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232084
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn>

    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_32_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    الوجی
    0.41
    rechte
    0.39
     kirj
    0.39
    શ્ર
    0.39
    SCOPE
    0.38
    efeuille
    0.38
    ijiet
    0.38
    meny
    0.37
    婢
    0.37
     सागरी
    0.36
    POSITIVE LOGITS
     pSig
    0.43
    觚
    0.37
     prominently
    0.36
     나는
    0.36
     tolerancia
    0.36
     தொழி
    0.35
     cầm
    0.35
     పో
    0.35
     আর্
    0.35
    鐧
    0.34
    Activations Density 0.002%

    No Known Activations