© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48005
    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_31_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
     رفتار
    0.41
     Eligibility
    0.40
    的行为
    0.39
    แทน
    0.37
    behav
    0.36
    疗
    0.35
    duk
    0.35
    herence
    0.35
     Level
    0.35
    شف
    0.35
    POSITIVE LOGITS
     enlargement
    0.45
     traffic
    0.42
     Metropolitana
    0.41
     comeback
    0.40
     enlarg
    0.40
     trafik
    0.40
    zion
    0.39
     mercenaries
    0.38
     loads
    0.38
     ഭ
    0.37
    Activations Density 0.000%

    No Known Activations