© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200291
    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_6_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
     ateliers
    1.30
    ب
    1.24
     arquivos
    1.20
     equipos
    1.20
     activos
    1.18
     argentinos
    1.17
     américains
    1.16
     judíos
    1.16
     acteurs
    1.14
     alguns
    1.13
    POSITIVE LOGITS
    ે
    1.09
    at
    0.99
    pose
    0.86
    ed
    0.84
    ound
    0.83
    sthrough
    0.83
    .
    0.82
    pressure
    0.78
    forest
    0.78
    ﻟ
    0.78
    Activations Density 0.000%

    No Known Activations