© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242445
    Prev
    Next
    INDEX
    Explanations

    `"$schema"` or `"$ref"` schemas

    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_40_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
     Cuisine
    0.43
    坤
    0.40
     зуб
    0.38
     cuisson
    0.37
    Ꮠ
    0.37
     MHC
    0.37
     odborn
    0.36
     سكس
    0.36
    க்கணக்கான
    0.36
     زائدا
    0.36
    POSITIVE LOGITS
     Roosevelt
    0.39
     Papers
    0.38
    തിൽ
    0.38
    활
    0.38
    Motion
    0.38
    وارد
    0.38
     قائمة
    0.36
     ફિલ્
    0.36
     Assets
    0.36
     papers
    0.35
    Activations Density 0.001%

    No Known Activations