© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228324
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
    ಕ್ತಿ
    0.40
     ಯಾರ
    0.40
     nahil
    0.39
    ຈັດສົ່ງ
    0.39
    剁
    0.38
     направлении
    0.38
     Люди
    0.37
     ಅರ್ಜಿ
    0.37
    냈
    0.37
     विश्वसनीय
    0.37
    POSITIVE LOGITS
     XX
    0.42
    ten
    0.41
     irland
    0.38
     Karne
    0.38
     X
    0.37
    XX
    0.37
    Amen
    0.35
    X
    0.35
    S
    0.34
    able
    0.34
    Activations Density 0.003%

    No Known Activations