© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38013
    Prev
    Next
    INDEX
    Explanations

    ata

    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_57_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
    िक्त
    0.35
     之
    0.35
    orts
    0.35
    䐍
    0.35
    ográficas
    0.34
    ట్
    0.34
    attendance
    0.34
    त्सा
    0.33
    がつ
    0.33
    linspace
    0.33
    POSITIVE LOGITS
    ata
    2.02
    ATA
    1.98
     ATA
    1.93
    타
    1.77
     ata
    1.74
     ta
    1.70
    ta
    1.68
    تا
    1.66
    اتا
    1.66
     Ata
    1.66
    Activations Density 0.010%

    No Known Activations