© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106658
    Prev
    Next
    INDEX
    Explanations

    Thai vowels and compounds

    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_1_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
    ем
    1.16
    ﺶ
    1.06
    지와
    0.98
    ਲ
    0.98
    ин
    0.95
     malicious
    0.90
    ＇
    0.89
    یم
    0.89
    𝗖
    0.87
    hoes
    0.86
    POSITIVE LOGITS
     (
    1.32
    dor
    1.10
    ka
    1.08
    ko
    1.05
     for
    1.05
     =
    1.05
     is
    1.02
    س
    1.01
     were
    1.00
            
    0.99
    Activations Density 0.000%

    No Known Activations