© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198023
    Prev
    Next
    INDEX
    Explanations

    guide to

    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_12_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
    idades
    0.53
     quir
    0.52
    ურად
    0.52
    顴
    0.52
     오늘도
    0.51
    ."))
    0.51
    izaciones
    0.49
     सुभाष
    0.49
    χος
    0.48
    :"))
    0.48
    POSITIVE LOGITS
    R
    0.61
    Out
    0.57
    Ke
    0.57
    Mol
    0.55
    )\
    0.54
    Week
    0.52
    O
    0.52
    \
    0.51
    Br
    0.50
    Ah
    0.50
    Activations Density 0.023%

    No Known Activations