© 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. 8220
    Prev
    Next
    INDEX
    Explanations

    bring in or issue

    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
    াণ
    0.38
    ಂತರ
    0.38
    formance
    0.37
    렐
    0.36
    Interval
    0.36
    ဏ
    0.36
     embaixo
    0.36
    隅
    0.35
    modif
    0.35
    垟
    0.35
    POSITIVE LOGITS
     issue
    0.50
     Issue
    0.47
     문제는
    0.46
     Issues
    0.45
    問題
    0.44
    问题
    0.44
     이슈
    0.43
    issue
    0.42
     main
    0.42
     issues
    0.42
    Activations Density 0.019%

    No Known Activations