© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83200
    Prev
    Next
    INDEX
    Explanations

    vim

    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_53_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
     Fluent
    0.42
    摫
    0.41
    спекти
    0.39
    捅
    0.39
    斑
    0.38
    谠
    0.38
    Styled
    0.38
    luents
    0.38
     Beng
    0.38
    Gav
    0.38
    POSITIVE LOGITS
     necessarily
    0.43
     sclerosis
    0.41
     MUR
    0.40
     golf
    0.39
     B
    0.38
     murder
    0.37
    rums
    0.36
     বুল
    0.36
    rim
    0.36
     Mur
    0.36
    Activations Density 0.002%

    No Known Activations