© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6259
    Prev
    Next
    INDEX
    Explanations

    softly, quietly, or gently

    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_39_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
     emoz
    0.43
     അടി
    0.43
    ⛈
    0.43
     lệch
    0.41
     मजा
    0.40
     نح
    0.39
     эмоциона
    0.39
     düz
    0.39
     പ്രവര്‍ത്തി
    0.39
    鯨
    0.39
    POSITIVE LOGITS
    quiet
    0.46
     silently
    0.43
    weird
    0.43
     softly
    0.42
     whispering
    0.42
    bits
    0.42
     quietly
    0.41
     quiet
    0.40
    Fre
    0.40
    Ton
    0.39
    Activations Density 0.129%

    No Known Activations