© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 69583
    Prev
    Next
    INDEX
    Explanations

    Renew

    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_46_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
     Hind
    0.42
     manipulator
    0.40
     figur
    0.39
    ELDS
    0.38
    Hind
    0.37
     Notes
    0.37
     ચ
    0.37
    stakes
    0.37
     manip
    0.37
    աց
    0.37
    POSITIVE LOGITS
    repo
    0.41
    帽
    0.38
    lv
    0.37
    oblot
    0.37
     desi
    0.36
    headline
    0.36
    rider
    0.36
    COVER
    0.35
    リュ
    0.35
    ạn
    0.35
    Activations Density 0.000%

    No Known Activations