© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30818
    Prev
    Next
    INDEX
    Explanations

    announcements for events and gatherings

    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
     kamb
    0.31
     arrang
    0.31
    êm
    0.30
    柬
    0.30
    檤
    0.30
     camb
    0.29
     compagn
    0.29
    >{</
    0.29
     codzien
    0.29
    encounter
    0.29
    POSITIVE LOGITS
     izinsuku
    0.37
     dates
    0.34
     সপ্তাহ
    0.34
     Tues
    0.33
     Dates
    0.32
     হবে
    0.32
     ориги
    0.31
     Woche
    0.31
    日は
    0.31
    Drinks
    0.31
    Activations Density 0.006%

    No Known Activations