© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41125
    Prev
    Next
    INDEX
    Explanations

    aneurysm

    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_22_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
    iería
    0.48
    nikom
    0.43
    mería
    0.40
     Synthetic
    0.39
    磬
    0.39
     vinegar
    0.39
    ニム
    0.39
     griego
    0.39
     MBBS
    0.39
     fatig
    0.39
    POSITIVE LOGITS
    κά
    0.44
     bracelet
    0.41
    ဟာ
    0.40
    Terror
    0.40
    atte
    0.39
    题
    0.39
    ustration
    0.38
     bracelets
    0.38
     moment
    0.38
     minute
    0.38
    Activations Density 0.002%

    No Known Activations