© 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. 197998
    Prev
    Next
    INDEX
    Explanations

    Estates

    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
     jouw
    0.57
    enje
    0.55
     summertime
    0.54
    ®.
    0.54
    komm
    0.53
    นิด
    0.52
    owników
    0.52
    lamide
    0.52
    eské
    0.52
    Kom
    0.51
    POSITIVE LOGITS
    i
    0.59
    p
    0.59
     bullets
    0.58
    βα
    0.55
    z
    0.55
    at
    0.54
    ින
    0.54
    تمر
    0.54
    вени
    0.53
    ри
    0.52
    Activations Density 0.001%

    No Known Activations