© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33430
    Prev
    Next
    INDEX
    Explanations

    C or si

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     тонн
    0.38
    markUp
    0.38
    ंगी
    0.38
    អារ
    0.37
     ใด
    0.37
    盛
    0.37
     beside
    0.36
    ্মার
    0.36
    ലിയ
    0.35
    ൂട്ട
    0.35
    POSITIVE LOGITS
     सी
    1.41
     si
    1.30
     سی
    1.18
     Si
    1.15
    Si
    1.15
     C
    1.10
     SI
    1.10
    si
    1.09
    सी
    0.98
     سي
    0.95
    Activations Density 0.002%

    No Known Activations