© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193559
    Prev
    Next
    INDEX
    Explanations

    understanding of

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㖵
    0.48
    ාව
    0.44
    íveis
    0.44
     Involvement
    0.41
     refuted
    0.40
     შესაძ
    0.40
    㧿
    0.39
     πί
    0.38
    육
    0.38
    䙲
    0.38
    POSITIVE LOGITS
     auto
    0.47
     ec
    0.41
     doa
    0.41
     inv
    0.41
     lam
    0.41
     saturate
    0.40
     balcony
    0.40
     hoi
    0.40
     complet
    0.39
     năm
    0.39
    Activations Density 0.001%

    No Known Activations