© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41208
    Prev
    Next
    INDEX
    Explanations

    mattress

    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_11_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
     S
    0.47
     ileri
    0.46
    alarını
    0.45
     माहित
    0.45
     Shelly
    0.44
    дку
    0.44
    shel
    0.43
    liang
    0.43
     Jin
    0.43
    kitten
    0.43
    POSITIVE LOGITS
    '))
    0.53
    '')
    0.48
    宒
    0.48
    㹮
    0.47
    ვი
    0.46
    '
    0.46
    ṱ
    0.46
    ')
    0.45
    "))
    0.45
    Television
    0.45
    Activations Density 0.015%

    No Known Activations