© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8629
    Prev
    Next
    INDEX
    Explanations

    Lima

    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_13_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
    いた
    0.55
    пикир
    0.53
     accompl
    0.52
     harvests
    0.50
    ികി
    0.50
    ಃ
    0.49
     !='')
    0.48
    getFocusAreas
    0.47
     postérieures
    0.47
    깁
    0.47
    POSITIVE LOGITS
    em
    0.54
    ot
    0.50
    ról
    0.49
     tabular
    0.49
    و
    0.47
     nonlinear
    0.47
    acterial
    0.47
     nylon
    0.47
    u
    0.46
    j
    0.46
    Activations Density 0.000%

    No Known Activations