© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30877
    Prev
    Next
    INDEX
    Explanations

    Okay, response

    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_50_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
    eps
    0.42
     rods
    0.40
    메
    0.40
    高铁
    0.39
    ThemeOverlay
    0.39
    lden
    0.38
     Schofield
    0.38
     Kaufman
    0.37
    rods
    0.37
    营
    0.37
    POSITIVE LOGITS
    ary
    0.42
    aries
    0.42
     Aks
    0.40
    ARY
    0.39
    вери
    0.39
     বিশেষণ
    0.39
     Such
    0.38
     UID
    0.38
    ARIES
    0.37
    韭
    0.37
    Activations Density 0.015%

    No Known Activations