© 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. 77936
    Prev
    Next
    INDEX
    Explanations

    pronunciation of sounds ("ch", "th", "dh")

    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
     circular
    0.39
     quit
    0.39
    秪
    0.38
     assent
    0.37
     shove
    0.37
     circle
    0.36
     approximate
    0.36
    *****/
    0.36
     ഒരു
    0.35
     aura
    0.35
    POSITIVE LOGITS
    Cur
    0.37
    塵
    0.37
    Kwa
    0.37
    Panic
    0.36
    Temp
    0.35
    TEMP
    0.35
     kapcsol
    0.34
    slideClass
    0.34
    Im
    0.34
    IM
    0.34
    Activations Density 0.015%

    No Known Activations