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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51299
    Prev
    Next
    INDEX
    Explanations

    peanuts and legumes

    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
     Winning
    0.37
     במש
    0.37
    игры
    0.36
    瓢
    0.36
    Ow
    0.36
    Fact
    0.36
    datad
    0.35
    ayama
    0.35
     Encu
    0.35
     Buyer
    0.34
    POSITIVE LOGITS
    GISLATIVE
    0.39
    ❸
    0.38
     flames
    0.35
    煐
    0.35
    द्वितीय
    0.35
    ogenetic
    0.34
    curité
    0.34
    varage
    0.34
     issued
    0.34
    ressor
    0.34
    Activations Density 0.008%

    No Known Activations