© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41189
    Prev
    Next
    INDEX
    Explanations

    withdrawal operations

    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_22_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
     uop
    0.41
     opér
    0.39
    オペ
    0.39
    ваемых
    0.38
    ⚐
    0.38
    ?]
    0.37
     ornamented
    0.37
     '?
    0.37
     коэффици
    0.37
    ?<
    0.37
    POSITIVE LOGITS
    Lat
    0.46
    racellular
    0.46
    Lod
    0.45
    ümü
    0.43
     LAT
    0.41
    Ph
    0.41
    Days
    0.41
     проце
    0.40
     peptid
    0.40
    latin
    0.40
    Activations Density 0.001%

    No Known Activations