© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212038
    Prev
    Next
    INDEX
    Explanations

    body pain

    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_20_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
    兽
    0.49
    獸
    0.49
    રે
    0.45
     periodical
    0.43
    oloog
    0.42
     setCount
    0.42
     playerCount
    0.41
     développe
    0.41
     numberOf
    0.41
     beast
    0.41
    POSITIVE LOGITS
    ataa
    0.45
     законодав
    0.45
    aktiv
    0.42
    iseksi
    0.41
    ")->
    0.40
     схо
    0.40
     fallout
    0.40
    Weber
    0.40
    ia
    0.39
     связан
    0.39
    Activations Density 0.002%

    No Known Activations