© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206786
    Prev
    Next
    INDEX
    Explanations

    grief

    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_6_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
    ’
    1.38
    There
    1.21
    पी
    1.20
    ”
    1.16
     There
    1.13
    आर
    1.02
    एस
    0.98
    ü
    0.97
    hhh
    0.96
    \
    0.95
    POSITIVE LOGITS
    ль
    0.96
    soever
    0.89
    ↵
    0.87
    м
    0.86
     fleeting
    0.86
    নে
    0.84
    ska
    0.82
     tedes
    0.82
     llev
    0.82
     Aplic
    0.80
    Activations Density 0.000%

    No Known Activations