© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33355
    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sw
    0.55
     Sw
    0.55
    Sw
    0.54
    sw
    0.44
    ฎ
    0.44
     Britton
    0.43
     swat
    0.41
     swarm
    0.41
     स्व
    0.41
    Saw
    0.39
    POSITIVE LOGITS
    ⾏
    0.40
     tapi
    0.39
    োয়ার
    0.39
    জর
    0.38
    જર
    0.37
     முடிய
    0.37
    ènes
    0.36
    ونکہ
    0.36
     குரு
    0.35
    ेंगी
    0.35
    Activations Density 0.005%

    No Known Activations