© 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. 168124
    Prev
    Next
    INDEX
    Explanations

    `var` followed by assignment or calculation

    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_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
     அலுவல
    0.39
    IPOP
    0.38
    YPE
    0.37
    拔
    0.36
     入
    0.36
     Volunteer
    0.36
     Interpol
    0.36
     १५
    0.36
    入
    0.34
     publicação
    0.34
    POSITIVE LOGITS
     souh
    0.38
     muff
    0.36
    aea
    0.36
    aeus
    0.35
    ιος
    0.34
    틸
    0.34
    Bobby
    0.33
     refunds
    0.32
    Comparer
    0.32
     tiled
    0.32
    Activations Density 0.002%

    No Known Activations