© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209145
    Prev
    Next
    INDEX
    Explanations

    looking

    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_56_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
     chuck
    0.49
     mad
    0.48
     cont
    0.45
     gig
    0.41
    𝐘
    0.40
     broken
    0.40
    Chuck
    0.40
     madr
    0.38
     Mad
    0.38
     inc
    0.38
    POSITIVE LOGITS
     الهم
    0.42
    長さ
    0.41
    댑
    0.41
     sc
    0.40
    togel
    0.39
     complains
    0.38
     Disorder
    0.37
    antara
    0.36
    <%=
    0.35
     <%=
    0.35
    Activations Density 0.002%

    No Known Activations