© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203964
    Prev
    Next
    INDEX
    Explanations

    bread

    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_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ayak
    0.47
     هسه
    0.38
    ᾳ
    0.38
     മാസ
    0.38
    Ik
    0.37
     পায়ের
    0.37
    Integr
    0.36
    ển
    0.36
    霭
    0.36
     நட
    0.36
    POSITIVE LOGITS
     CBR
    0.55
     GBM
    0.49
    webBrowser
    0.45
     CMB
    0.45
    ක්‍
    0.45
     ceb
    0.44
     TBR
    0.44
    クリ
    0.43
     CFR
    0.43
    كري
    0.43
    Activations Density 0.000%

    No Known Activations