© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143550
    Prev
    Next
    INDEX
    Explanations

    neural graphics 3D

    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_46_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
     precipitation
    0.41
     hidden
    0.39
    楇
    0.39
     excavation
    0.38
     APC
    0.37
    ခြ
    0.36
     cleanup
    0.36
     trac
    0.36
     thanksgiving
    0.36
    遮
    0.36
    POSITIVE LOGITS
    COL
    0.46
    द्वितीय
    0.40
     COL
    0.40
     Colton
    0.39
     Colt
    0.38
    Shannon
    0.38
    thol
    0.38
    туи
    0.38
    attu
    0.37
    Twenty
    0.37
    Activations Density 0.002%

    No Known Activations