© 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. 317
    Prev
    Next
    INDEX
    Explanations

    guides

    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
     सु
    0.44
     Ob
    0.39
     Faithful
    0.39
    秤
    0.38
    डिज
    0.37
     Sylvain
    0.37
    αιν
    0.37
    Ct
    0.36
     چار
    0.36
    ▎
    0.36
    POSITIVE LOGITS
    guides
    0.47
     guides
    0.45
    ガイド
    0.42
     guide
    0.41
    running
    0.39
     Guides
    0.39
     slides
    0.39
    Slides
    0.39
    prevent
    0.38
    guide
    0.38
    Activations Density 0.024%

    No Known Activations