© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115296
    Prev
    Next
    INDEX
    Explanations

    svg markup

    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_27_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
     ಪ್ರದೇಶ
    0.40
    ແລະ
    0.38
    でも
    0.37
    userdetails
    0.36
    硏
    0.36
     подобных
    0.36
     इति
    0.35
    人士
    0.35
     વિસ્ત
    0.35
    })$-
    0.34
    POSITIVE LOGITS
    ängel
    0.40
     क्विंटल
    0.39
     Esther
    0.38
     accesses
    0.37
     gebracht
    0.36
     deducting
    0.36
    юще
    0.36
    睄
    0.36
     Ob
    0.36
     പറയുന്നത്
    0.36
    Activations Density 0.001%

    No Known Activations