© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156407
    Prev
    Next
    INDEX
    Explanations

    Metta meditation

    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
    Negative Logits
    、
    1.27
    ى
    1.22
    1.13
    1.07
    اذ
    1.05
    1.05
    اج
    1.04
    1.04
     powied
    1.03
    In
    1.02
    POSITIVE LOGITS
    های
    1.70
    ك
    1.63
    یت
    1.44
     the
    1.42
    ка
    1.42
     aider
    1.34
    на
    1.30
    들이
    1.27
     imagining
    1.27
    ,
    1.27
    Activations Density 0.000%

    No Known Activations