© 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. 63067
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
     ful
    0.37
     negligent
    0.37
    的文件
    0.37
     files
    0.36
    파일
    0.36
     文件
    0.36
    暉
    0.36
    たす
    0.35
    隨著
    0.35
     δυ
    0.35
    POSITIVE LOGITS
     DRI
    0.37
     வார்த்த
    0.36
     Qxc
    0.35
     লাফ
    0.32
    drill
    0.32
    DRI
    0.32
     mathvariant
    0.32
    ವಾಡ
    0.31
    ㈡
    0.31
     IMS
    0.31
    Activations Density 0.002%

    No Known Activations