© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135494
    Prev
    Next
    INDEX
    Explanations

    main role or subject

    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_1_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
    ר
    1.51
     for
    1.38
    ุ
    1.16
    ג
    1.12
    ↵↵
    1.11
     ответствен
    1.07
    f
    1.07
     that
    1.06
     активность
    1.05
    ر
    1.04
    POSITIVE LOGITS
    it
    1.11
    lek
    1.01
    komst
    1.01
    gunakan
    0.98
    ah
    0.97
    ens
    0.96
    ul
    0.92
    ken
    0.88
    queline
    0.86
    ahul
    0.85
    Activations Density 0.001%

    No Known Activations