© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3523
    Prev
    Next
    INDEX
    Explanations

    Chinese and Thai syllables

    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_39_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
    )、
    0.31
    ﾍ
    0.31
     NE
    0.30
    NE
    0.29
     資
    0.29
    且
    0.29
    𝓻
    0.29
     Chinese
    0.29
    isted
    0.28
     nuest
    0.28
    POSITIVE LOGITS
    UIColor
    0.28
     Woolf
    0.28
    LAYER
    0.28
    篙
    0.27
    cję
    0.27
     empir
    0.26
     خالص
    0.26
    ിക്കാം
    0.26
     есте
    0.26
     Cálculo
    0.25
    Activations Density 0.040%

    No Known Activations