© 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. 77880
    Prev
    Next
    INDEX
    Explanations

    adverbs from words ending in -ly

    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
    -
    0.54
    lingual
    0.45
    mm
    0.45
    \-
    0.42
    ox
    0.40
    kes
    0.40
    id
    0.40
    lightblue
    0.40
    imal
    0.39
    referenced
    0.39
    POSITIVE LOGITS
    лари
    0.48
    赌
    0.41
     رجسٹریشن
    0.41
    カートリッジ
    0.41
     volontà
    0.40
    Ⲓ
    0.40
     calcS
    0.39
     verità
    0.39
     جیل
    0.38
     évén
    0.38
    Activations Density 0.005%

    No Known Activations