© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 7038
    Prev
    Next
    INDEX
    Explanations

    end of turn

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     eut
    0.39
     hú
    0.37
    戾
    0.37
     eun
    0.36
     Esh
    0.35
     manures
    0.35
     pounded
    0.35
     pound
    0.34
     lut
    0.34
     শু
    0.34
    POSITIVE LOGITS
    Sierra
    0.43
     സാ
    0.40
    iete
    0.39
     Sacred
    0.38
    েম্বরে
    0.38
     золо
    0.38
    뇰
    0.38
     sacar
    0.38
    ember
    0.38
    xlab
    0.37
    Activations Density 0.063%

    No Known Activations