© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16650
    Prev
    Next
    INDEX
    Explanations

    rate or success rate

    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_40_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
     الميل
    0.35
    کنش
    0.34
     ז
    0.34
     Sw
    0.34
    壤
    0.33
     หน่วย
    0.33
     नवा
    0.32
     ਡ
    0.32
     Vip
    0.32
     Priv
    0.32
    POSITIVE LOGITS
     rate
    1.98
     rates
    1.97
     Rate
    1.84
     Rates
    1.83
    Rate
    1.72
    rate
    1.71
     RATE
    1.70
    Rates
    1.67
    率
    1.64
    rates
    1.63
    Activations Density 0.144%

    No Known Activations