© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237920
    Prev
    Next
    INDEX
    Explanations

    spoken dialogue prefixes

    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_32_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
     geometri
    0.42
    ၻ
    0.40
     সম্পাদকীয়
    0.38
     sigh
    0.38
    త్ప
    0.38
     fulfilment
    0.36
     sighs
    0.36
    話
    0.35
     fulfill
    0.35
    電話
    0.34
    POSITIVE LOGITS
    讲
    0.42
     Encore
    0.41
     liqu
    0.41
     তালে
    0.41
     عصر
    0.39
    לח
    0.38
     لمدة
    0.38
    受欢迎
    0.38
    iane
    0.38
     الأص
    0.37
    Activations Density 0.000%

    No Known Activations