© 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
    2. Gemma-3-27B-IT
    3. 18-GEMMASCOPE-2-TRANSCODER-262K
    4. 88437
    Prev
    Next
    INDEX
    Explanations

    tangy, tart, sour, or acidic flavors

    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_18_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
     relics
    0.47
    ್ರೀ
    0.46
    テ
    0.43
    辺
    0.41
    ridges
    0.41
    chocolate
    0.41
    代
    0.41
    ólica
    0.40
     Budget
    0.39
    宗
    0.38
    POSITIVE LOGITS
     mnog
    0.54
     ብዙውን
    0.53
     zobraz
    0.50
    "]="
    0.49
    orpion
    0.48
     நம்
    0.48
     Giveen
    0.47
    "]
    0.47
    มากมาย
    0.46
     Gmail
    0.46
    Activations Density 0.003%

    No Known Activations