© 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. 209080
    Prev
    Next
    INDEX
    Explanations

    say Original

    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
     OW
    0.40
     OH
    0.40
     oh
    0.39
     อุ
    0.38
     Oh
    0.38
    啊
    0.37
     Ow
    0.37
     啊
    0.37
    '?
    0.36
     aw
    0.36
    POSITIVE LOGITS
    enter
    0.53
     Enter
    0.53
     “
    0.53
     enter
    0.53
    Enter
    0.50
    entered
    0.43
    进入
    0.42
     (“
    0.41
    ENTER
    0.40
     entered
    0.39
    Activations Density 0.006%

    No Known Activations