© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168894
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    もあり
    0.44
     due
    0.43
     devido
    0.41
     owing
    0.39
    ைகளால்
    0.39
     achieving
    0.38
     cascades
    0.38
     asteroids
    0.37
    崢
    0.37
     debido
    0.37
    POSITIVE LOGITS
     शकतात
    0.38
     መጠ
    0.37
     ይጠ
    0.37
     Stand
    0.35
     खर्च
    0.34
     averiguar
    0.34
     Leg
    0.34
    ่วม
    0.33
     ಸೂಚ
    0.33
    noop
    0.33
    Activations Density 0.000%

    No Known Activations