© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161570
    Prev
    Next
    INDEX
    Explanations

    #include

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     बताने
    0.39
    扳
    0.37
     Users
    0.37
     Info
    0.37
    請
    0.36
     practiced
    0.36
     annals
    0.36
    萆
    0.36
    ຯ
    0.36
     thrown
    0.35
    POSITIVE LOGITS
    羞
    0.38
     Einwilligung
    0.38
    长江
    0.37
    Philosophy
    0.37
    保证金
    0.37
    Holland
    0.36
    твор
    0.36
     конкурс
    0.36
    VK
    0.36
     نہایت
    0.36
    Activations Density 0.000%

    No Known Activations