© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127783
    Prev
    Next
    INDEX
    Explanations

    let's

    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_37_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
     rokov
    0.45
    भ
    0.41
    owskiego
    0.40
    ிருக்கிறார்
    0.38
    supply
    0.38
    IRO
    0.38
     ---------
    0.38
     răsp
    0.38
    attaque
    0.37
    न्देल
    0.37
    POSITIVE LOGITS
    ioned
    0.42
     preventing
    0.40
     אנ
    0.40
    Prevent
    0.39
    DIM
    0.39
    prevent
    0.37
    }\|\
    0.36
     কাউ
    0.35
     lub
    0.35
     جلوگیری
    0.35
    Activations Density 0.033%

    No Known Activations