© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24843
    Prev
    Next
    INDEX
    Explanations

    text manipulation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    humidity
    0.41
    стые
    0.39
    Lb
    0.39
    rouw
    0.38
    ＰＥ
    0.38
    Für
    0.38
    杷
    0.38
    Рус
    0.37
     Selbst
    0.37
    PosZ
    0.37
    POSITIVE LOGITS
     sa
    0.56
     ek
    0.55
     ny
    0.55
     k
    0.53
     th
    0.53
     mai
    0.53
     e
    0.52
     te
    0.52
     ș
    0.52
     mi
    0.51
    Activations Density 0.073%

    No Known Activations