© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159628
    Prev
    Next
    INDEX
    Explanations

    Chinese syllables with 'ng' or 'ang' ending

    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_2_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
    t
    1.83
    f
    1.50
    d
    1.42
    down
    1.26
    dien
    1.16
    től
    1.16
    to
    1.15
    ton
    1.11
    、
    1.11
    can
    1.10
    POSITIVE LOGITS
    و
    1.15
    ти
    0.98
    ’.
    0.98
    -
    0.96
    দের
    0.96
     σε
    0.94
    ’,
    0.92
     stems
    0.92
     fixes
    0.92
     murders
    0.91
    Activations Density 0.001%

    No Known Activations