© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205614
    Prev
    Next
    INDEX
    Explanations

    research defense

    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_20_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
    Q
    0.15
    from
    0.15
    PM
    0.14
    ชื่อ
    0.14
    beach
    0.14
    contained
    0.14
    Beach
    0.14
    ​
    0.14
    CC
    0.14
    nombre
    0.14
    POSITIVE LOGITS
     aktif
    0.16
     intuit
    0.15
     Hyg
    0.15
     ont
    0.15
     enthusi
    0.14
     Anybody
    0.14
    ترل
    0.14
     anyone
    0.14
     beklen
    0.14
     consape
    0.14
    Activations Density 0.002%

    No Known Activations