© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 79863
    Prev
    Next
    INDEX
    Explanations

    say "am"

    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_53_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
    鈔
    0.40
    န်
    0.39
    Ara
    0.39
    SON
    0.39
     Apar
    0.39
    旷
    0.39
     হাড়
    0.38
    钞
    0.38
    Clique
    0.37
    Fra
    0.37
    POSITIVE LOGITS
    apanam
    0.48
    assem
    0.46
    uric
    0.42
    ilem
    0.41
     am
    0.41
    ayam
    0.41
     Corinth
    0.40
    peek
    0.40
    am
    0.39
    jam
    0.39
    Activations Density 0.002%

    No Known Activations