© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135343
    Prev
    Next
    INDEX
    Explanations

    versiones / versátil

    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
    Negative Logits
    on
    1.83
    at
    1.71
    ا
    1.58
    ت
    1.52
    ين
    1.51
    as
    1.45
    त
    1.38
    of
    1.37
    ل
    1.25
     has
    1.24
    POSITIVE LOGITS
    )
    1.02
    )’
    1.02
     zawier
    0.95
    )」
    0.89
    gruppen
    0.88
    ),
    0.87
    )».
    0.85
     لگاتا
    0.85
    )...
    0.84
     کھیلو
    0.84
    Activations Density 0.001%

    No Known Activations