© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197046
    Prev
    Next
    INDEX
    Explanations

    rate limiting 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_9_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
    chaoxing
    0.54
    agai
    0.51
     contractName
    0.51
    ጉ
    0.50
    غا
    0.49
     maximizes
    0.49
     genitalia
    0.49
    itemName
    0.48
     സംഘ
    0.47
     koleg
    0.47
    POSITIVE LOGITS
    드가
    0.54
    2
    0.52
    恩
    0.47
    larak
    0.46
     Replacement
    0.45
     Diabetic
    0.45
     os
    0.44
     قيم
    0.44
    OPTV
    0.44
    你了
    0.43
    Activations Density 0.000%

    No Known Activations