© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89406
    Prev
    Next
    INDEX
    Explanations

    company suffixes

    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_23_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
     sump
    0.37
     musste
    0.34
    (!(
    0.34
    вості
    0.34
    рее
    0.33
    GPS
    0.33
    (~
    0.33
    規
    0.33
    recording
    0.33
     〜
    0.33
    POSITIVE LOGITS
    ැන
    0.39
     Trendy
    0.37
    伲
    0.37
     President
    0.37
     Team
    0.37
     /**
    0.36
     Leaders
    0.35
     खरीदारी
    0.35
     শ্রেণির
    0.35
     leveraging
    0.35
    Activations Density 0.000%

    No Known Activations