© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 200061
    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_27_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
    監督
    0.39
    চর্
    0.38
     moveTo
    0.38
     obeys
    0.38
     confesses
    0.38
     admit
    0.37
    副
    0.37
     confess
    0.36
    紀
    0.35
     செல்க
    0.35
    POSITIVE LOGITS
     Carpathian
    0.37
     Alcohol
    0.36
     dérou
    0.36
     গাড়
    0.35
     Roller
    0.35
    تهم
    0.35
    race
    0.35
    roller
    0.35
    鬚
    0.35
     قطعة
    0.34
    Activations Density 0.000%

    No Known Activations