© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158202
    Prev
    Next
    INDEX
    Explanations

    adverbs 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
    v
    1.84
    re
    1.44
    st
    1.41
    ال
    1.39
    ।
    1.34
    al
    1.33
    te
    1.31
    tr
    1.30
    il
    1.29
    ve
    1.29
    POSITIVE LOGITS
    ного
    1.16
     стане
    1.13
     gebruiken
    1.04
     къ
    0.98
     vám
    0.96
    orte
    0.95
     könne
    0.93
    ї
    0.92
     gebru
    0.91
     зеле
    0.91
    Activations Density 0.001%

    No Known Activations