© 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. 78154
    Prev
    Next
    INDEX
    Explanations

    two things are the same

    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
     সমান
    0.32
     Equival
    0.31
     서로
    0.31
    겹
    0.30
    相等
    0.29
    相同
    0.29
     рав
    0.29
     डिस्क्रिप्शन
    0.29
     identical
    0.29
    相同的
    0.28
    POSITIVE LOGITS
     mores
    0.31
    льга
    0.30
    发出
    0.29
     Av
    0.29
     tare
    0.29
     relativ
    0.28
    辣
    0.28
     তাড়
    0.28
    激光
    0.27
    发
    0.27
    Activations Density 0.013%

    No Known Activations