© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108091
    Prev
    Next
    INDEX
    Explanations

    adverb 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_2_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
    ক
    1.23
    ین
    1.06
    1.05
    speople
    1.03
     amphibians
    1.02
     antigens
    1.00
    r
    0.99
     продуктов
    0.96
     источников
    0.96
    sn
    0.96
    POSITIVE LOGITS
    在
    1.59
    ли
    1.38
    ви
    1.32
    一
    1.30
    لي
    1.21
    نتي
    1.21
    ל
    1.20
    يد
    1.18
    ويل
    1.16
    被
    1.13
    Activations Density 0.000%

    No Known Activations